The appropriate maintenance of highway roads is critical for the safe operation of road networks and conserves maintenance costs. Multiple methods have been developed to investigate the surface of roads for various types of cracks and potholes, among other damage. Like road surface damage, the condition of expansion joints in concrete pavement is important to avoid unexpected hazardous situations. Thus, in this study, a new system is proposed for autonomous expansion joint monitoring using a vision-based system. The system consists of the following three key parts: (1) a camera-mounted vehicle, (2) indication marks on the expansion joints, and (3) a deep learning-based automatic evaluation algorithm. With paired marks indicating the expansion joints in a concrete pavement, they can be automatically detected. An inspection vehicle is equipped with an action camera that acquires images of the expansion joints in the road. You Only Look Once (YOLO) automatically detects the expansion joints with indication marks, which has a performance accuracy of 95%. The width of the detected expansion joint is calculated using an image processing algorithm. Based on the calculated width, the expansion joint is classified into the following two types: normal and dangerous. The obtained results demonstrate that the proposed system is very efficient in terms of speed and accuracy.

The administration of regional neuraxial analgesia for pain relief during labor is widely recognized as a safe and effective method involving medication delivery into the epidural or subarachnoid space in the lower back. This study proposes an innovative semantic image segmentation methodology emphasizing enhanced interpretability using convolutional Random Fourier Features and layer-wise weighted class-activation maps tailored explicitly for foot segmentation in regional analgesia monitoring. Namely, our contribution is twofold: i) a novel Random Fourier Features layer is introduced to deal with image data to enhance three well-known architectures (FCN, UNet, and ResUNet); ii) three novel quantitive measures are presented to evaluate the interpretability of a given deep learning model devoted to segmentation tasks. Our approach is rigorously evaluated on a demanding dataset of foot thermal images from pregnant women who received epidural anesthesia. Its small size and considerable variability characterize the dataset. Our validation results demonstrate that the proposed methodology not only achieves competitive foot segmentation performance but also significantly enhances the explainability of the process, rendering it well-suited for applications such as epidural insertion during labor.

The current neural networks for tomato leaf disease recognition have problems such as large model parameters, long training time, and low model accuracy. To solve these problems, a lightweight convolutional neural network LBFNet is proposed in this paper.First, a lightweight convolutional neural network LBFNet is established as the base model. Secondly, a three-channel attention mechanism module is introduced to learn the disease features in tomato leaf disease images and reduce the interference of redundant features. Finally, a cascade module is introduced to increase the depth of the model, solve the gradient descent problem, and reduce the loss caused by increasing the depth of the model. The quantized pruning technique is also used to further compress the model parameters and optimize the model performance. The results show that the LBFNet model achieves 99.06% accuracy on the LBFtomato dataset, with a training time of 996s and a single classification accuracy of over 94%. Further training using the saved weight file after quantized pruning makes the model accuracy reach 97.66%. Compared with the base model, the model accuracy was improved by 28%, and the model parameters were reduced by 96.7% compared with the traditional Resnet50. It was found that LBFNet can quickly and accurately identify tomato leaf diseases in complex environments, providing effective assistance to agricultural producers.

Global models have been developed to tackle the challenge of forecasting sets of series that are related or share similarities, but not for heterogeneous datasets. Various methods of partitioning by relatedness have been introduced to enhance the similarities of the set, resulting in improved forecasting accuracy but often at the cost of a reduced sample size, which could be harmful. To shed light on how the relatedness between series impacts the effectiveness of global models in real-world demand forecasting problems we perform an extensive empirical study using the M5 competition dataset. We examined cross-learning scenarios driven by the product hierarchy commonly employed in retail planning, which allow global models to capture interdependencies across products and regions more effectively. Our findings show that global models outperform state-of-the-art local benchmarks by a considerable margin, indicating that they are not inherently more limited than local models and can handle unrelated time series data effectively. The accuracy of data partitioning approaches increases, as the size of the data pools and the models' complexity decrease. However, there is a trade-off between data availability and data relatedness. Smaller data pools lead to increased similarity among time series, making it easier to capture cross-product and cross-region dependencies, but this comes at the cost of a reduced sample, which may not be beneficial. Finally, it's worth noting that the successful implementation of global models for heterogeneous datasets can significantly impact forecasting practice.

Automated spectrum analysis serves as a troubleshooting tool that helps to diagnose faults in wireless networks like difficult signal propagation conditions and coexisting wireless networks. It provides a higher monitoring coverage while requiring less expertise compared to manual spectrum analysis. In this paper, we introduce a data set that can be used to train and evaluate deep learning models, capable of detecting frames from different wireless standards as well as interference between single frames. Since manually labelling a high variety of frames in different environments is too challenging, an artificial data generation pipeline has been developed. The data set consists of 20 000 augmented signal segments, each containing a random number of different Wi-Fi and Bluetooth frames, their spectral image representations and labels that describe the position and type of frame within the spectrogram. The data set contains results of intermediate processing steps that enables the research or teaching community to create new data sets for specific requirements or to provide new interesting examination examples.

The use of digital twins for the development of Autonomous Maritime Surface Vessels (AMSVs) has enormous potential to resolve the increasing need for water-based navigation and safety at the seas. Aiming at the problem of lack of broad and integrated digital twin implementations with live data along with the absence of a digital twin-driven framework for AMSV design and development, an application framework for the development of a fully autonomous vessel using an integrated digital twin in a 3D simulation environment has been presented. Our framework has four layers to ensure that the simulation and the real-world boat as well as the environment are as close as possible. Åboat, an experimental research platform for maritime automation and autonomous surface ship applications, equipped with two trolling electric motors, cameras, LiDARs, IMU and GPS has been used as the case study to provide a proof of concept. Åboat and its sensors, alongwith the environment have been replicated in a 3D simulation environment. Using the proposed application framework, we develop obstacle detection and path planning systems based on machine learning which leverage live data from a 3D simulation environment to mirror the complex dynamics of the real world.

Deep convolutional neural networks (CNNs) have been widely used in various medical imaging tasks. However, due to the intrinsic locality of convolution operation, CNNs generally cannot model long-range dependencies well, which are important for accurately identifying breast cancer from unregistered multi-view mammograms. This motivates us to leverage the architecture of Vision Transformers to capture long-range relationships of multiple mammograms from the same patient. For this purpose, we employ local Transformer blocks to separately learn patch relationships within a specific view (CC/MLO) of one side (right/left) of mammogram. The outputs from different views and sides are concatenated and fed into global Transformer blocks, to jointly learn patch relationships between two different views of the left and right breasts. To evaluate the proposed model, we retrospectively assembled a dataset involving 949 sets of CC and MLO view mammograms, which include 470 malignant cases and 479 normal or benign cases. We trained and evaluated the model using a five-fold cross-validation method. Without any arduous preprocessing steps (e.g., optimal window cropping, chest wall or pectoral muscle removal, two-view image registration, etc.), our two-view Transformer-based model achieves lesion classification accuracy of 77.0% and area under ROC curve (AUC = 0.814), outperforming state-of-the-art multi-view CNNs by 3.1% and 3%, respectively. Meanwhile, the new two-view model improves mammographic case classification accuracies of two single-view models by 7.4% (CC) and 4.5% (MLO), respectively. The promising results unveil the great potential of using Transformers to develop high-performing computer-aided diagnosis (CADx) schemes of mammography.

Melanoma is considered to be the most aggressive form of skin cancer. Due to the similar shape of malignant and benign cancerous lesions, doctors spend considerably more time when diagnosing these findings. At present, the evaluation of malignancy is performed primarily by invasive histological examination of the suspicious lesion. Developing an accurate classifier for early and efficient detection can minimize and monitor the harmful effects of skin cancer and increase patient survival rates. This paper proposes a multi-class classification task using the CoAtNet architecture, a hybrid model that combines the depthwise convolution matrix operation of traditional convolutional neural networks with the strengths of Transformer models and self-attention mechanics to achieve better generalization and capacity. The proposed multi-class classifier achieves an overall precision of 0.901, recall 0.895, and AP 0.923, indicating high performance compared to other state-of-the-art networks.

This work aims to develop an autonomous system for the unmanned aerial vehicle (UAV) to land on a moving platform such as the automobile or marine vessels, providing a promising solution for a long-endurance flight operation, a large mission coverage range, and a convenient recharging ground station. Different from most state-of-the-art UAV landing frameworks which rely on UAV’s onboard computers and sensors, the proposed system fully depends on the computation unit situated on the ground vehicle/marine vessel to serve as a landing guidance system. Such novel configuration can therefore lighten the burden of the UAV and computation power on the ground vehicle/marine vessel could be enhanced. In particular, we exploit a sensor fusion-based algorithm for the guidance system to perform UAV localization, whilst a control method based upon trajectory optimization is integrated. Indoor and outdoor experiments are conducted and the result shows that a precise autonomous landing on a 43 X 43 cm platform could be performed.

In an industrial environment, the quality assurance of weld seams requires extensive efforts. The most commonly used methods for that are expensive and time-consuming destructive tests, since quality assurance procedures are difficult to integrate into production processes. Beyond that, available test methods allow only the assessment of a very limited set of characteristics. They are either suitable for determining selected geometric features or for locating and evaluating internal seam defects. The presented work describes an evaluation methodology based on microfocus X-ray computed tomography scans (µCT scans) which enable the 3D characterization of weld seams, including internal defects such as cracks and pores. A 3D representation of the weld contour, i.e., the complete geometry of the joint area in the component with all quality-relevant geometric criteria, is an unprecedented novelty. Both the dimensions of the weld seam and internal defects can be revealed, quantified with a resolution down to a few micrometers and precisely assigned to the welded component. On the basis of the methodology developed within the framework of this study, the results of the scans performed on the alloy AA 2219 can be transferred to other aluminum alloys. In this way, the data evaluation framework can be used to obtain extensive reference data for the calibration and validation of inline process monitoring systems employing Deep Learning-based data processing.

As a relatively high percentage of adenoma polyps are missed, a computer-aided diagnosis (CAD) tool based on deep learning can aid the endoscopist in diagnosing colorectal polyps or colorectal cancer in order to decrease polyps missing rate and prevent colorectal cancer mortality. Convolutional Neural Network (CNN) is a deep learning method and has achieved better results in detecting and segmenting specific objects in images in the last decade than conventional models such as regression, support vector machines or artificial neural networks. In recent years, based on the studies in medical imaging criteria, CNN models have acquired promising results in detecting masses and lesions in various body organs, including colorectal polyps. In this review, the structure and architecture of CNN models and how colonoscopy images are processed as input and converted to the output are explained in detail. In most primary studies conducted in the colorectal polyp detection and classification field, the CNN model has been regarded as a black box since the calculations performed at different layers in the model training process have not been clarified precisely. Furthermore, I discuss the differences between the CNN and conventional models, inspect how to train the CNN model for diagnosing colorectal polyps or cancer, and evaluate model performance after the training process.

Macula fovea detection is a crucial prerequisite towards screening and diagnosing macular diseases. Without early detection and proper treatment, any abnormality involving the macula may lead to blindness. However, with the ophthalmologist shortage and time-consuming artificial evaluation, neither accuracy nor effectiveness of the diagnose process could be guaranteed. In this project, we proposed a deep learning approach on ultra-widefield fundus (UWF) images for macula fovea detection. This study collected 2300 ultra-widefield fundus images from Shenzhen Aier Eye Hospital in China. Methods based on U-shape network (Unet) and Fully Convolutional Networks (FCN) are implemented on 1800 (before amplifying process) training fundus images, 400 (before amplifying process) validation images and 100 test images. Three professional ophthalmologists were invited to mark the fovea. A method from the anatomy perspective is investigated. This approach is derived from the spatial relationship between macula fovea and optic disc center in UWF. A set of parameters of this method is set based on the experience of ophthalmologists and verified to be effective. Results are measured by calculating the Euclidean distance between proposed approaches and the accurate grounded standard, which is detected by Ultra-widefield swept-source optical coherence tomograph (UWF-OCT) approach. Through a comparation of proposed methods, we conclude that, deep learning approach of Unet outperformed other methods on macula fovea detection tasks, by which outcomes obtained are comparable to grounded standard method.

Aim: To determine whether an AI model and single sensor measuring acceleration and ECG could model cognitive and physical fatigue for a self-paced trail run. Methods: A field-based protocol of continuous fatigue repeated hourly induced physical (~45 minutes) and cognitive (~10 minutes) fatigue on one healthy participant. Physical load was a 3.8 km, 200 m vertical gain, trail run with acceleration and electrocardiogram (ECG) data collected using a single sensor. Cognitive load was a Multi Attribute Test Battery (MATB) and separate assessment battery including the Finger Tap Test (FTT), Stroop, Trail Making A and B, Spatial Memory, Paced Visual Serial Addition Test (PVSAT), and a vertical jump. A fatigue prediction model was implemented using a Convolutional Neural Network (CNN). Results: When the fatigue test battery results were compared for sensitivity to the protocol load, FTT right hand (R2 0.71) and Jump Height (R2 0.78) were the most sensitive while the other tests were less sensitive (R2 values Stroop 0.49, Trail Making A 0.29, Trail Making B 0.05, PVSAT 0.03, spatial memory 0.003). Best prediction results were achieved with a rolling average of 200 predictions (102.4 s), during set activity types, mean absolute error for ‘walk up’ (MAE200 12.5%) and range of absolute error for ‘run down‘ (RAE200 16.7%). Conclusion: We were able to measure cognitive and physical fatigue using a single wearable sensor during a practical field protocol including contextual factors in conjunction with a neural network model. This research has practical application to fatigue research in the field.

Annotating training data is a time consuming and labor intensive process in deep learning, especially for images with many objects present. In this paper, we propose a method to allow deep networks to be trained on data with reduced numbers of annotations (per image) in heatmap regression tasks (e.g. object detection and counting), by applying an asymmetric loss function. In a real scenario, this reduction of annotations can be imposed by the researchers (e.g. ask the annotators to label only 50% of what they see in each image), or can potentially counteract unintentionally missing labels from the annotators. To demonstrate the effectiveness of our method, we conduct experiments in two domains, crowd counting and wheat spikelet detection, using different deep network architecture. We drop various percentages of instance annotations per image in training. Results show that an asymmetric loss function is effective across different models and datasets, even in very extreme cases with limited annotations provided (e.g. 90% of the original annotations reduced). Whilst tuning of the key parameters are required, we find that setting conservative parameter values can help more realistic situations, where only small amounts of data have been missed by annotators.

Background: White matter hyperintensities (WMH), of presumed vascular origin, are visible and quantifiable neuroradiological markers of brain parenchymal change. These changes may range from damage secondary to inflammation and other neurological conditions, through to healthy ageing. Fully automatic WMH quantification methods are promising, but still, traditional semi-automatic methods seem to be preferred in clinical research. We systematically reviewed the literature for fully automatic methods developed in the last five years, to assess what are considered state-of-the-art techniques, as well as trends in the analysis of WMH of presumed vascular origin. Method: We registered the systematic review protocol with the International Prospective Register of Systematic Reviews (PROSPERO), registration number - CRD42019132200. We conducted the search for fully automatic methods developed from 2015 to July 2020 on Medline, Science direct, IEE Explore, and Web of Science. We assessed risk of bias and applicability of the studies using QUADAS 2. Results: The search yielded 2327 papers after removing 104 duplicates. After screening titles, abstracts and full text, 37 were selected for detailed analysis. Of these, 16 proposed a supervised segmentation method, 10 proposed an unsupervised segmentation method, and 11 proposed a deep learning segmentation method. Average DSC values ranged from 0.538 to 0.91, being the highest value obtained from an unsupervised segmentation method. Only four studies validated their method in longitudinal samples, and eight performed an additional validation using clinical parameters. Only 8/37 studies made available their method in public repositories. Conclusions: We found no evidence that favours deep learning methods over the more established k-NN, linear regression and unsupervised methods in this task. Data and code availability, bias in study design and ground truth generation influence the wider validation and applicability of these methods in clinical research.

The small satellite market continues to grow year after year. A compound annual growth rate of 17% is estimated during the period between 2020 and 2025. Low-cost satellites can send a vast amount of images to be post-processed at the ground to improve the quality and extract detailed information. In this domain lies the resolution enhancement task, where a low-resolution image is converted to a higher resolution automatically. Deep learning approaches to Super-Resolution (SR) reached the state-of-the-art in multiple benchmarks; however, most of them were studied in a single-frame fashion. With satellite imagery, multi-frame images can be obtained at different conditions giving the possibility to add more information per image and improve the final analysis. In this context, we developed and applied to the PROBA-V dataset of multi-frame satellite images a model that recently topped the European Space Agency’s Multi-frame Super Resolution (MFSR) competition. The model is based on proven methods that worked on 2D images tweaked to work on 3D: the Wide Activation Super Resolution (WDSR) family. We show that with a simple 3D CNN residual architecture with WDSR blocks and a frame permutation technique as data augmentation better scores can be achieved than with more complex models. Moreover, the model requires few hardware resources, both for training and evaluation, so it can be applied directly from a personal laptop.

This article presents an automated vision-based algorithm for the die-scale inspection of wafer images captured using scanning acoustic tomography (SAT). This algorithm can find defective and abnormal die-scale patterns, and produce a wafer map to visualize the distribution of defects and anomalies on the wafer. The main procedures include standard template extraction, die detection through template matching, pattern candidate prediction through clustering, and pattern classification through deep learning. To conduct the template matching, we first introduce a two-step method to obtain a standard template from the original SAT image. Subsequently, a majority of the die patterns are detected through template matching. Thereafter, the columns and rows arranged from the detected dies are predicted using a clustering method; thus, an initial wafer map is produced. This map is composed of detected die patterns and predicted pattern candidates. In the final phase of the proposed algorithm, we implement a deep learning-based model to determine defective and abnormal patterns in the wafer map. The experimental results verified the effectiveness and efficiency of our proposed algorithm. In conclusion, the proposed method performs well in identifying defective and abnormal die patterns, and produces a wafer map that presents important information for solving wafer fabrication issues.

Interest in drone solutions in forestry applications is growing. Using drones, datasets can be captured flexibly and at high spatial and temporal resolutions when needed. In forestry applications, fundamental tasks include the detection of individual trees, tree species classification, bio-mass estimation, etc. Deep Neural Networks (DNN) have shown superior results when comparing with conventional machine learning methods such as Multi-Layer Perceptron (MLP) in cases of huge input data. The objective of this research was to investigate 3D convolutional neural networks (3D-CNN) to classify three major tree species in a boreal forest: pine, spruce, and birch. The proposed 3D-CNN models were employed to classify tree species in a test site in Finland. The classifiers were trained with a dataset of 3039 manually labelled trees. Then the accuracies were assessed by employing independent datasets of 803 records. To find the most efficient set of feature combination, we compare the performances of 3D-CNN models trained with hyperspectral (HS) channels, RGB channels, and canopy height model (CHM), separately and combined. It is demonstrated that the proposed 3D-CNN model with RGB and HS layers produces the highest classification accuracy. The producer accuracy of the best 3D-CNN classifier on the test dataset were 99.6%, 94.8%, and 97.4% for pines, spruces, and birches, respectively. The best 3D-CNN classifier produced ~5% better classification accuracy than the MLP with all layers. Our results suggest that the proposed method provides excellent classification results with acceptable performance metrics for HS datasets. Our results show that pine class was detectable in most layers. Spruce was most detectable in RGB data, while birch was most detectable in the HS layers. Furthermore, the RGB datasets provide acceptable results for many low-accuracy applications.

Deep behavioral covariates (DBCs) introduced in this perspective form a new class of covariates that have the potential to enhance the performance of predictive models and improve analytics in clinical decision support applications. DBCs can measure how engaged a patient tends to be and how he or she tends to respond to events, and they may be highly predictive of the patient’s outcomes for a planned treatment. DBCs may potentially serve as a standard to measure patient engagement and activation and may form highly efficient mechanisms for improving patient outcomes.

The basal ganglia (BG) are a central component of the brain, crucial to the initiation, execution and learning of adaptive actions. The BG are the major site of the action of dopamine. An important aspect of the BG architecture is the existence of two paths, direct and indirect, having different projection targets and dopamine receptor expression. To understand the BG, dopamine, and related disorders, it is imperative to understand the two paths. The standard account used in neuroscience research for decades posits that the role of the direct path is to support movements, while that of the indirect path is to suppress unselected or completed movements. This account is contradicted by converging evidence. Here, we explain why the arguments supporting the standard account are flawed, and present a new account, in which the role of the indirect path is completely opposite: to support automated execution. During acute events, the direct path allows coarse responses. These are refined by competition, and the resulting focused response is executed and learned by the indirect path, assisted by cholinergic interneurons and the subthalamic nucleus (STN). The new account allows a novel understanding of the symptoms of Parkinson's disease, in particular tremor and rigidity, and of its treatment by STN deep brain stimulation.

Timely detection of surface damages on wind turbine blades is imperative for minimising downtime and avoiding possible catastrophic structural failures. With recent advances in drone technology, a large number of high-resolution images of wind turbines are routinely acquired and subsequently analysed by experts to identify imminent damages. Automated analysis of these inspection images with the help of machine learning algorithms can reduce the inspection cost, thereby reducing the overall maintenance cost arising from the manual labour involved. In this work, we develop a deep learning based automated damage suggestion system for subsequent analysis of drone inspection images. Experimental results demonstrate that the proposed approach could achieve almost human level precision in terms of suggested damage location and types on wind turbine blades. We further demonstrate that for relatively small training sets advanced data augmentation during deep learning training can better generalise the trained model providing a significant gain in precision.

This study proposes a mobile positioning method which adopts recurrent neural network algorithms to analyze the received signal strength indications from heterogeneous networks (e.g., cellular networks and Wi-Fi networks) for estimating the locations of mobile statioThis study proposes a mobile positioning method which adopts recurrent neural network algorithms to analyze the received signal strength indications from heterogeneous networks (e.g., cellular networks and Wi-Fi networks) for estimating the locations of mobile stations. The recurrent neural networks with multiple consecutive timestamps can be applied to extract the features of time series data for the improvement of location estimation. In practical experimental environments, there are 4,525 records, 59 different base stations, and 582 different Wi-Fi access points detected in Fuzhou University in China. The lower location errors can be obtained by the recurrent neural networks with multiple consecutive timestamps (e.g., 2 timestamps and 3 timestamps); the experimental results can be observed that the average error of location estimation was 9.19 meters by the proposed mobile positioning method with 2 timestamps.

In recent years, weeds is responsible for most of the agricultural yield losses. To deal with this threat, farmers resort to spraying pesticides throughout the field. Such method not only requires huge quantities of herbicides but impact environment and humans health. One way to reduce the cost and environmental impact is to allocate the right doses of herbicide at the right place and at the right time (Precision Agriculture). Nowadays, Unmanned Aerial Vehicle (UAV) is becoming an interesting acquisition system for weeds localization and management due to its ability to obtain the images of the entire agricultural field with a very high spatial resolution and at low cost. Despite the important advances in UAV acquisition systems, automatic weeds detection remains a challenging problem because of its strong similarity with the crops. Recently Deep Learning approach has shown impressive results in different complex classification problem. However, this approach needs a certain amount of training data but, creating large agricultural datasets with pixel-level annotations by expert is an extremely time consuming task. In this paper, we propose a novel fully automatic learning method using Convolutional Neuronal Networks (CNNs) with unsupervised training dataset collection for weeds detection from UAV images. The proposed method consists in three main phases. First we automatically detect the crop lines and using them to identify the interline weeds. In the second phase, interline weeds are used to constitute the training dataset. Finally, we performed CNNs on this dataset to build a model able to detect the crop and weeds in the images. The results obtained are comparable to the traditional supervised training data labeling. The accuracy gaps are 1.5% in the spinach field and 6% in the bean field.

Deep learning has recently attracted much attention due to its excellent performance in processing audio, image, and video data. However, few studies are devoted to the field of automatic modulation classification (AMC). It is one of the most well-known research topics in communication signal recognition, which remains challenging for traditional methods due to the complex disturbance from other sources. This paper proposes a heterogeneous deep model fusion (HDMF) method to solve the problem in a unified framework. The contributions include: 1) The convolutional neural network (CNN) and long short-term memory (LSTM) are combined by two different ways without prior knowledge involved; 2) A large database, including eleven types of single-carrier modulation signals with various noises as well as a fading channel, is collected with various signal-to-noise ratios (SNRs) based on a real geographical environment; and 3) Experimental results demonstrate that HDMF is super capable of copping with the AMC problem, and achieves much better performance when compared with the independent network. The source code and the database will be publically available.

Sensitivity to weather conditions, and specially to clouds, is a severe limiting factor to the use of optical remote sensing for Earth monitoring applications. A possible alternative, is to resort to weather-insensitive synthetic aperture radar (SAR) images. However, in many real-world applications, critical decisions are made based on some informative spectral features, such as water, vegetation or soil indices, which cannot be extracted from SAR images. In the absence of optical sources, these data must be estimated. The current practice is to perform linear interpolation between data available at temporally close time instants. In this work, we propose to estimate missing spectral features through data fusion and deep-learning. Several sources of information are taken into account - optical sequences, SAR sequences, DEM - so as to exploit both temporal and cross-sensor dependencies. Based on these data, and a tiny cloud-free fraction of the target image, a compact convolutional neural network (CNN) is trained to perform the desired estimation. To validate the proposed approach, we focus on the estimation of the normalized difference vegetation index (NDVI), using coupled Sentinel-1 and Sentinel-2 time-series acquired over an agricultural region of Burkina Faso from May to November 2016. Several fusion schemes are considered, causal and non-causal, single-sensor or joint-sensor, corresponding to different operating conditions. Experimental results are very promising, showing a significant gain over baselines methods according to all performance indicators.

In any document, graphical elements like tables, figures, and formulas contain essential information. The processing and interpretation of such information require specialized algorithms. Off-the-shelf OCR components cannot process this information reliably. Therefore, an essential step in document analysis pipelines is to detect these graphical components. It leads to a high-level conceptual understanding of the documents that makes digitization of documents viable. Since the advent of deep learning, the performance of deep learning-based object detection has improved many folds. In this work, we outline and summarize the deep learning approaches for detecting graphical page objects in the document images. Therefore, we discuss the most relevant deep learning-based approaches and state-of-the-art graphical page object detection in document images. This work provides a comprehensive understanding of the current state-of-the-art and related challenges. Furthermore, we discuss leading datasets along with the quantitative evaluation. Moreover, it discusses briefly the promising directions that can be utilized for further improvements.

Through the development of the metaverse concept from the Sumerian myth (5500 - 1800 BC) and mind-altering novel, “Snow Crash” in 1992, to today’s information age, human- and society-centred urban metaverse worlds, an extension of residents and urban society where the virtual and the physically real blend and are more organically integrated, are meant to mirror the fabric of urban life with no harm to their residents. The success of urban metaverse cybercommunities depends on the quality of data-driven Smart City (SC) Digital Twins (DTs), the seamless exchange of data between cyber and physical worlds (e.g. between residents and their counterpart “Avatars’’) and the processing of the data effectively and efficiently with no vicious interventions. The potential risks in this ecosystem that incorporates Web3 can be extremer than the ones in Web2 since users are immersed with multiple tightly coupled wearable sensor-rich devices perceiving the blend of the real and the virtual with possible imminent negative experiences. This study, by analysing potential cyberthreats in the urban metaverse cyberspaces, proposes a blockchain-based Decentralised Privacy-Preserving Machine Learning (DPPML) authentication and verification technique, which uses the metaverse immersive devices and can be instrumented effectively against identity impersonation and theft of credentials, identity, or avatars.

Currently, the Bangladeshi financial sector is undergoing significant transformations. With the expansion of the infrastructure and the increasing prevalence of digital banking services, it is essential to take measures to prevent cyberattacks. These threats can be effectively mitigated through the utilization of deep learning and machine learning techniques. Through the analysis of massive amounts of banking data in real-time, these methods make it possible to detect and prevent malicious software, fraud, and security breaches that are proactive. Because the government is actively pushing for financial inclusion and digitalization, strong cybersecurity measures are more important than they have ever been. It is the purpose of this study to investigate the application of deep learning and machine learning to improve the cybersecurity environment of Bangladesh’s banking sector in light of the country’s rapidly expanding digital economy.

This article presents a low-cost insurance system developed for small-hold farms in disaster-prone regions, primarily using free Earth Observation (EO) data and Free Open Source Software (FOSS) – collectively termed sustainable geoinformatics - with a proprietary mobile phone app that enables verification. The study examined 30 farms in Risaralda department, Colombia. A Digital Elevation Model (12.5m pixels) from the ALOS PALSAR satellite sensor was used with a Geographical Information System (GIS) to map the terrain, drainage and geohazards of each farming district. Google Earth Engine (GEE) was used to carry out Time Series Analysis of 15 EO and weather datasets for 1998 to 2020. This analysis enabled the levels of risk from hydrometeorological hazards to be determined for each farm of the study, providing key data for the setting of insurance premiums. A parametric insurance product was piloted using GPS-tagged, time-stamped mobile phone photos to verify crop health. Key features of this insurance system are its low operational cost and rapid damage verification, relative to conventional approaches to farm insurance. It is an affordable form of insurance for small-scale farmers, with the rapid verification and payment of claims. This relatively fast, low-cost and affordable approach to insurance for small-scale farming enhances sustainable development by enabling policy-holder farmers to recover more quickly from disasters.

As the world increasingly becomes more interconnected, the demand for safety and security is ever-increasing, particularly for industrial networks. This has prompted numerous researchers to investigate different methodologies and techniques suitable for intrusion detection systems (IDS) requirements. Over the years, many studies have proposed various solutions in this regard including signature-based and machine-learning (ML) based systems. More recently, researchers are considering deep learning (DL) based anomaly detection approaches. Most proposed works in this research field aimed to achieve either one or a combination of high accuracy, considerably low false alarm rates (FARs), high classification specificity and detection sensitivity, achieving lightweight DL models, or other ML and DL-related performance measurement metrics. In this study, we propose a novel method to convert a raw dataset to an image dataset to magnify patterns. Based on this we devise an anomaly detection for IDS using a lightweight convolutional neural network (CNN) that classifies denial of service and distributed denial of service. The proposed methods were evaluated using a modern dataset, CSE-CIC-IDS2018, and a legacy dataset, NSL-KDD. We have also applied a combined dataset to assess the generalization of the proposed model across various datasets. Our experimental results have demonstrated that the proposed methods achieved high accuracy and considerably low FARs with high specificity and sensitivity. The resulting loss and accuracy curves have also demonstrated the excellent generalization of the proposed lightweight CNN model, effectively avoiding overfitting. This holds for both the modern and legacy datasets, including their mixed version.

Accurate short-term solar irradiance forecasting is crucial for the efficient operation of solar energy driven photovoltaic (PV) power plants. In this research, we introduce a novel hybrid ensemble forecasting model that amalgamates the strengths of machine learning tree-based models and deep learning neuron-based models. The hybrid ensemble model integrates the interpretability of tree-based models with the capacity of neuron-based models to capture complex temporal dependencies within solar irradiance data. Furthermore, stacking and voting ensemble strategies are employed to harness the collective strengths of these models, significantly enhancing prediction accuracy. This integrated methodology is enhanced by incorporating pixels from satellite images provided by the European Organization for the Exploitation of Meteorological Satellites (EUMETSAT). These pixels are converted into structured data arrays and employed as exogenous inputs in the algorithm. The primary objective of this study is to improve the accuracy of short-term solar irradiance predictions, spanning a forecast horizon up to 6 hours ahead. The incorporation of EUMETSAT satellite image pixels data enables the model to extract valuable spatial and temporal information, thus enhancing the overall forecasting precision. This research also includes detailed analysis of the derivation of GHI using satellite images. The study was carried out and the models tested across three distinct locations in Austria. A detailed comparative analysis was carried out for traditional Satellite (SAT) and Numerical Weather Prediction (NWP) models with hybrid models. Our findings demonstrate a higher skill score for all of the approaches compared to smart persistent model and consistently highlight the superiority of the hybrid ensemble model for short-term prediction window of 1 to 6 hours. This research underscores the potential for enhanced accuracy of the hybrid approach to advance short-term solar irradiance forecasting, emphasizing its effectiveness at understanding the intricate interplay of the meteorological variables affecting solar energy generation worldwide. The results of this investigation carry noteworthy implications for advancing solar energy systems, thereby supporting the sustainable integration of renewable energy sources into the electrical grid.

Panoramic and periapical radiograph tools help dentists diagnose the most common dental diseases. Generally, dentists identify dental caries manually by inspecting X-ray images. However, due to their heavy workload, or poor image quality, dentists may sometimes overlook some unnoticeable dental caries, which may ultimately hinder the patient treatment. The purpose of this study was to develop an algorithm that classifies the teeth X-Ray images into three categories of “Normal”, “Caries”, and “Filled”. Our study used a dataset of 116 patients and 3712 single teeth images for training, validation and testing. Images were pre-processed using a sharpening filter and an intensity color map. We used a pre-trained transfer learning model, the NASNetMobile, which served as the feature extractor and the Convolutional Neural Network (CNN) model served as the classifier. The training dataset had a “Recall” of 0.92, 0.90 and 0.91 for “Normal”, “Caries” and “Filled” respectively and the test dataset had a “Recall” of 0.86, 0.81 and 0.85 for “Normal”, “Caries” and “Filled” respectively. The classification of the teeth X-Rays was successful and can be valuable for dentist as the artificial intelligence algorithm can serve as a decision support tool to aid dentists when they need to diagnose dental treatment.

Attempts to use computers to aid in the detection of breast malignancies date back more than 20 years. Despite significant interest and investment, this has historically led to minimal or no significant improvement in performance and outcomes with traditional computer aided detection. However, recent advances in artificial intelligence and machine learning are now starting to deliver on the promise of improved performance. There are at present more than 20 FDA approved AI applications for breast imaging, but adoption and utilization are widely variable and overall low. Breast imaging is unique and has aspects that create both opportunities and challenges for AI development and implementation. Breast cancer screening programs worldwide rely on screening mammography to reduce the morbidity and mortality of breast cancer and many of the most exciting research and available AI applications focus on cancer detection for mammography. There are however multiple additional potential applications for AI in breast imaging including decision support, risk assessment, breast density quantitation, workflow and triage, quality evaluation, response to neoadjuvant chemotherapy assessment, and image enhancement. In this review the current status, availability, and future directions of investigation of these applications are discussed, as well as the opportunities and barriers to more widespread utilization.

Anomaly detection is an active area of research with numerous methods and applications. This survey reviews the state-of-the-art of data-driven anomaly detection techniques and their application to the the aviation domain. After a brief introduction to the main traditional data-driven methods for anomaly detection, we review the recent advances in the area of neural networks, deep learning and temporal-logic based learning. We cover especially unsupervised techniques applicable to time series data because of their relevance to the aviation domain, where the lack of labeled data is the most usual case, and the nature of flight trajectories and sensor data is sequential, or temporal. The advantages and disadvantages of each method are presented in terms of computational efficiency and detection efficacy. The second part of the survey explores the application of anomaly detection techniques to aviation and their contributions to the improvement of the safety and performance of flight operations and aviation systems. As far as we know, some of the presented methods have not yet found an application in the aviation domain. We review applications ranging from the identification of significant operational events in air traffic operations to the prediction of potential aviation system failures for predictive maintenance.

Tables in the document image are one of the most important entities since they contain crucial information. Therefore, accurate table detection can significantly improve information extraction from tables. In this work, we present a novel end-to-end trainable pipeline, HybridTabNet, for table detection in scanned document images. Our two-stage table detector uses the ResNeXt-101 backbone for feature extraction and Hybrid Task Cascade (HTC) to localize the tables in scanned document images. Moreover, we replace conventional convolutions with deformable convolutions in the backbone network. This enables our network to detect tables of arbitrary layouts precisely. We evaluate our approach comprehensively on ICDAR-13, ICDAR-17 POD, ICDAR-19, TableBank, Marmot, and UNLV. Apart from the ICDAR-17 POD dataset, our proposed HybridTabNet outperforms earlier state-of-the-art results without depending on pre and post-processing steps. Furthermore, to investigate how the proposed method generalizes unseen data, we conduct an exhaustive leave-one-out-evaluation. In comparison to prior state-of-the-art results, our method reduces the relative error by 27.57% on ICDAR-2019-TrackA-Modern, 42.64% on TableBank (Latex), 41.33% on TableBank (Word), 55.73% on TableBank (Latex + Word), 10% on Marmot, and 9.67% on UNLV dataset. The achieved results reflect the superior performance of the proposed method.

In this paper, we redefine the boundaries of blood cell classification, expanding from 5 to 11 distinct blood cell types using the challenging 11-class PBC dataset. This shift enables a deeper understanding of blood cell diversity, overcoming previous limitations in medical image analysis. Our approach combines state-of-the-art deep learning techniques, including pre-trained ConvNets, ViTb16 models, and custom CNN architectures. We employ transfer learning, fine-tuning, and ensemble strategies, such as CBAM and Averaging ensembles, to achieve unprecedented accuracy and interpretability. Our fully fine-tuned EfficientNetV2 B0 model sets a new standard, with a macro-average precision, recall, and F1-score of 91%, 90%, and 90%, respectively, and an average accuracy of 93%. This breakthrough underscores the transformative potential of 11-class blood cell classification for more precise medical diagnoses. Moreover, our groundbreaking "Naturalize" augmentation technique produces remarkable results. The 2K-PBC dataset generated with "Naturalize" boasts a macro-average precision, recall, and F1-score of 97%, along with an average accuracy of 96% when leveraging the fully fine-tuned EfficientNetV2 B0 model. This innovation not only elevates classification performance but also addresses data scarcity and bias in medical deep learning. Our research marks a paradigm shift in blood cell classification, enabling more nuanced and insightful medical analyses. The "Naturalize" technique’s impact extends beyond blood cell classification, emphasizing the vital role of diverse and comprehensive datasets in advancing healthcare applications through deep learning.

The Global natural and manmade events are exposing the fragility of the tourism industry and its impact on the global economy. Prior to the COVID-19 pandemic, tourism contributed 10.3% to the global GDP and employed 333 million people but saw a significant decline due to the pandemic. Sustainable and smart tourism requires collaboration from all stakeholders and a comprehensive understanding of global and local issues to drive responsible and innovative growth in the sector. This paper presents an approach for leveraging big data and deep learning to dis-cover holistic, multi-perspective (e.g., local, cultural, national, and international) and objective information on a subject. Specifically, we develop a machine learning pipeline to extract parameters from academic literature and public opinions on Twitter, providing a unique and comprehensive view of the industry from both academic and public perspectives. The academic-view dataset was created from the Scopus database and contains 156,759 research articles from 2000 to 2022, which were modelled to identify 33 distinct parameters in 4 categories: Tourism Types, Planning, Challenges, and Media & Technologies. A Twitter dataset of 485,813 tweets was collected over 18 months starting March 2021 to August 2022 to showcase public perception of tourism in Saudi Arabia, which was modelled to reveal 13 parameters categorized into two broader sets: Tourist Attractions and Tourism Services. Discovering system parameters are re-quired to embed autonomous capabilities in systems and for decision-making and problem-solving during system design and operations. The proposed approach improves AI-based information discovery by extending the use of scientific literature, Twitter, and other sources for autonomous, dynamic optimizations of systems, promoting novel research in the tourism sector and contributing to the development of smart and sustainable societies. The paper also presents a comprehensive knowledge structure and literature review of the tourism sector based on over 250 research articles.

General Theory of Information (GTI) offers a groundbreaking framework for designing "mindful machines" that bridge the divide between biological intelligence and digital automation. GTI reimagines traditional computing by introducing cognitive, autopoietic (self-regulating) capabilities in digital systems, enabling them to perceive, adapt, and respond autonomously to changing conditions. Unlike conventional AI and AGI models that operate within predefined algorithmic constraints, GTI-based systems go beyond by incorporating self-awareness and a resilient digital "self," capable of storing interaction histories and learning from them. This paper explores GTI’s practical applications in systems requiring resilience, cognition, and ethical safeguards. In video streaming and medical assistance, GTI-based digital genomes enable systems to function independently, actively self-correct, and conform to policy-driven ethical standards. These mindful machines embody unique traits rarely achieved with traditional AI: robust resilience through self-corrective mechanisms, adaptive learning from accumulated experiences, and alignment with ethical principles that govern system behavior. In demonstrating how GTI can cultivate resilience, autonomy, and ethical decision-making, this paper reveals GTI’s potential to empower digital automata with human-like adaptability and values. As such, GTI emerges as a bridge to a new generation of digital systems designed not merely to execute but to understand, adapt, and ethically engage within complex real-world environments.

Welding spot defect detection using deep learning methods provides an effective way of body-in-white quality monitoring. Based on the existing Faster R-CNN model, this paper proposed an improved faster R-CNN model for resistance welding spot surface defect inspection to improve inspection efficiency and accuracy. The model contains the following improvements. Firstly, the improved algorithm uses anchor box with higher confidence output by the RPN network to locate welding spots. When a defect is detected and the detection system is in a suspended state, the Fast R-CNN network is used to confirm the defect category and details. Secondly, a new pruning model is proposed to replace the entire backbone neural network, which unnecessary convolutional layers and connection layers are deleted, and some parameters of each hidden layer are further reduced. On the premise of ensuring detection accuracy, the parameter quantity is extremely reduced, and the speed is improved. Experiments show that the model proposed in this paper took about 15ms for one single image test, and both the detection accuracy and recall rate reached over 90% according to the test on our dataset. This deep learning model meets the requirements of welding spot defect detection.

Background and Objectives: Acute aortic dissection (AD) is a life-threatening condition and early detection can significantly improve patient outcomes and survival. This study evaluates the clinical benefits of integrating a deep-learning (DL)-based application for automated detection and prioritisation of AD on chest CT angiographies (CTAs), focusing on the reduction of scan-to-assessment (STAT) and interpretation times (IT). Materials and Methods: This retrospective Multi-Reader, Multi-Case (MRMC) study compared AD detection with and without artificial intelligence-(AI) assistance. Ground truth was established by two U.S. board-certified radiologists, while three additional expert radiologists participated as readers. All participants assessed the same CTAs without AI-assistance (pre-AI arm) and, after a 1-month washout period, with the help of the device outputs (post-AI arm). STAT and IT were compared between the two phases. Results: The study included 285 CTAs (95 per reader, per arm), with a mean patient age of 58.5 years ±14.7(SD), 52% men, 37% prevalence. AI assistance significantly reduced STAT for detecting 33 true positive AD cases, from 15.84 minutes (95% CI: 13.37–18.31min) without AI to 5.07 minutes (95% CI: 4.23–5.91min) with AI, a 68% reduction (p<0.01). IT also decreased significantly, from 21.22 seconds (95% CI: 19.87–22.58s) without AI to 14.17 seconds (95% CI: 13.39–14.95s) with AI (p<0.05). Conclusions: Integrating a DL-based algorithm for AD detection on chest CTAs significantly reduces both STAT and IT. By prioritising the most urgent cases, AI ensures faster diagnosis and improves the workflow efficiency in clinical radiology practice, compared to standard First-In First-Out (FIFO) workflow.

In the study of mountainous areas, mountain peaks play a vital role as geomorphic features that have significant influence on hydrological processes, vegetation distribution, and other important topographic characteristics. From the perspectives of geomorphology and hydrology, the river network water system is an interconnected entity that serves as a crucial component in describing regional topography, geomorphology, and hydrological features. The primary objective of this article is to extract water system information and mountain peak data in Chongli District, Hebei Province. To extract mountain peaks, coarse-resolution Digital Elevation Model (DEM) data is utilized to estimate their positions and initiate data sampling based on DEM elevations. Deep learning models are employed to avoid explicit feature extraction and instead implicitly learn from training data. By using weight sharing techniques, the training parameters of the network are reduced, achieving more accurate extraction and recognition of mountain peaks in Chongli District, along with their classification. For the extraction of the water system, the fast regional convolutional neural network algorithm from target detection is introduced to enhance the efficiency and accuracy of extracting water system information through image processing. This algorithm rapidly identifies the type, location, and width of the water systems. Additionally, the AlexNet transfer learning method is applied to locate the river skeleton within the extracted water system area. Morphological methods are then used to extract river morphology and calculate its length and width. Finally, a developed algorithm for water system information extraction detects the presence of water system coverage areas in Chongli District. Through experiments, a total of 2792 mountain peak data points were successfully extracted. In terms of water system information extraction, the Faster R-CNN and CNN-based methods demonstrate high efficiency and low detection rates. This study provides information services and data support for the operation and maintenance of the Chongli Winter Olympics. Furthermore, it serves as a reference for future research conducted by scholars in the Chongli area, offering insights into various fields such as environmental changes, vegetation classification, and geomorphic features.

Reliable prediction of building-level energy demand is crucial for the building managers to optimize and regulate energy consumption. Conventional prediction models omit the uncertainties associated with demand over time; hence, they are mostly inaccurate and unreliable. In this study, a Bayesian neural network (BNN)-based probabilistic prediction model is proposed to tackle this challenge. By quantifying the uncertainty, BNNs provide probabilistic predictions that capture the variations in the energy demand. The proposed model is trained and evaluated on a subset of the building operations dataset of Lawrence Berkeley National Laboratory (LBNL), Berkeley, California, which includes diverse attributes related to climate and key building performance indicators. We have performed thorough hyperparameter tuning and used fixed-horizon validation to evaluate trained models on various test data to assess generalization ability. To validate the results, quantile random forest (QRF) was used as a benchmark. The study compared BNN with LSTM, showing that BNN outperformed LSTM in uncertainty quantification.

Crowd abnormal behavior recognition is one of the research hotspots in computer vision. Its goal is to use computer vision technology and abnormal behavior detection models to accurately perceive, predict, and intervene in potential abnormal behaviors of the crowd, and monitor the status of the crowd system in public places in real-time, to effectively prevent and deal with public security risks and ensure public life safety and social order. To this end, focusing on the crowd abnormal behavior recognition technology in the computer vision system, a systematic review study of its theory and cutting-edge technology is conducted. First, the crowd level and abnormal behaviors in public places are defined, and the challenges faced by crowd abnormal behavior recognition are expounded. Then, from the dimensions based on traditional methods and based on deep learning, the mainstream technologies of abnormal behavior recognition are discussed, and the design ideas, advantages, and limitations of various methods are analyzed. Next, the mainstream software tools are introduced to provide a comprehensive reference for the technical framework; Secondly, typical abnormal behavior datasets at home and abroad are sorted out, and the characteristics of these datasets are compared in detail from multiple perspectives such as scale, characteristics and uses, and the performance indicators of different algorithms on the datasets are compared and analyzed; Finally, the full text is summarized and the future development direction of crowd abnormal behavior recognition technology is prospected.

As the adoption of deep learning models continues to surge across various applications, the need for efficient deployment architectures becomes increasingly critical. This paper presents a novel approach to enhance the deployment of deep learning models by leveraging serverless architecture. Serverless computing has been popular for its auto-scaling, cost-effectiveness, and simplified management characteristics. However, the intense resource demands of deep learning models pose challenges in maintaining low response times and effective load balancing within serverless environments. The proposed architecture addresses these challenges by integrating principles from both deep learning model optimization and serverless computing. Through systematic experimentation and analysis, we demonstrate that by appropriately designing and tuning the deployment architecture, significant improvements in response time, performance, resource utilization, and load distribution can be achieved.

Mobile health technologies enable continuous, quantitative assessment of mobility and gait in real-world environments, facilitating early diagnosis of gait disorders, disease progression monitoring, and prediction of adverse events like falls. Traditionally, mobile gait assessment predominantly relied on body-fixed sensors positioned at the feet or lower trunk. Here, we investigate the potential of an algorithm utilizing an ear-worn motion sensor for spatiotemporal segmentation of gait patterns. We collected 3D acceleration profiles from the ear-worn sensor during varied walking speeds in 53 healthy adults. Temporal convolutional networks were trained to detect stepping sequences and predict spatial relations between steps. The resulting algorithm, mEar, accurately detects initial and final ground contacts (F1 score of 99% and 91%, respectively). It enables determination of temporal and spatial gait cycle characteristics (among others stride time and stride length) with good to excellent validity at a precision sufficient to monitor clinically relevant changes in walking speed, stride-to-stride variability, and side asymmetry. This study highlights the ear as a viable site for monitoring gait and proposes its potential integration with in-ear vital sign monitoring. Such integration offers a practical approach to comprehensive health monitoring and telemedical applications, by integrating multiple sensors in a single anatomical location.

Groundnut is an oil seed cash crop, that can be consumed directly by humans and animals. It is also used as an intelligence in the industrial production of butter and other products. However, Groundnut seeds can become infected with fungi, viruses, pests, physical damage, and high heat, which can negatively impact crop yield, quality, and economic value, and pose health hazards. To address these challenges, computer vision technology detects and classifies defects. This study introduced an ensemble deep learning defected classification model that combines VGG16 and InceptionV3 using seed images. To enhance model performance, collected images are preprocessed using novel techniques tailored to different image types. Preprocessing techniques are chosen based on image-quality evaluation metrics. Watershed segmentation is applied followed by detecting the region of interest in the image using YOLOv3. The image dataset is augmented and balanced using a Generative Adversarial Network (GAN). The model development involves a combination of classical and deep-based features, comparing features extracted with (HOG and GLCM) to those extracted with InceptionV3 and VGG16. The ensemble model achieves an accuracy of 96.25% with a split ratio of 10% for testing, 10% for validation, and 80% for training set. This research benefits farmers looking to improve yield, consumers of groundnut products, and researchers studying seed defects. The work provides valid insights for future researchers regarding dataset creation, augmentation, methods, and feature selection for modeling. However, the model experienced misclassifications due to the similar appearance of sample images in different classes. Future researchers should address these challenges and consider factors such as oil content and defect grading.

With the rapid development of Intelligent Transportation Systems (ITS), vehicle type classification, as a key link in Automatic Toll Collection systems (ATC), is of great significance in improving traffic efficiency and reducing economic losses. This study proposes an intelligent vehicle classification system based on deep learning and multi-sensor data fusion to address the accuracy issues existing in vehicle classification methods based on optical sensors (OS) and human observers. The system significantly improves the accuracy and robustness of vehicle classification by combining deep Convolutional Neural Networks (CNN), LiDAR sensors, and machine learning algorithms. We first constructed a large-scale annotated dataset containing multiple vehicle types and complex traffic scenes to improve our model's capability to identify different vehicle characteristics. Next, CNN models based on different architectures were designed to extract global and local features of the vehicle, respectively. In addition, the LiDAR sensor was used to achieve the spatial structure architectures of the vehicle and combined with the output of the CNN model to improve classification performance under occlusion and complex scenes.

Accurate forecasting of available energy portion that corresponds to the reservoir inflow of the month(s) ahead provides important decision support for the hydropower plants in energy pro-duction planning for revenue maximization, as well as for the environmental impact prevention, and flood control at the upstream and downstream of a basin. Therefore, a reliable forecasting tool or model is deemed necessary and crucial. Considering the fluctuation and nonlinearity of data which significantly influence the forecasting results, this study develops an effective hybrid model by integrating Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) called “PSO-ANN” model based on the hydrological and meteorological data pre-processed by cross-correlation function (CCF), autocorrelation function (AFC), and normalization techniques for predicting the available energy portion corresponding to the reservoir inflow mentioned above for a case study hydropower plant in Laos namely, Theun-Hinboun hydropower plant (THHP). The model was evaluated by using correlation coefficient (r), relative error (RE), root mean square error (RMSE), and Taylor diagram plots in comparison with the popular single algorithm approaches such as ANN, and NARX models. Results demonstrated the superiority of the proposed PSO-ANN approach over the other two models.

Amidst the escalating demands for efficient Intelligent Transportation Systems (ITS) management, the significance of accurate Origin-Destination (OD) data prediction has emerged as a paramount concern, given its indispensable role in the ITS domain. This paper introduces a groundbreaking integrated model, creatively fusing the unique strengths of Graph Convolutional Network (GCN), Residual Neural Network (ResNet), and Long Short-Term Memory Network (LSTM) into a single architecture, which we name GraphResLSTM, to exploit road segment average speed data for OD prediction. Compared with conventional road segment traffic volume data, average speed data is more readily available, significantly reducing the data accessibility barrier for OD prediction. We underscore the critical role of selection of key road segments and employs a combination of Entropy Weight Method and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to identify 41 representative road segments from the experimental road network. In the experimental phase, we simulate 86400000 seconds of traffic conditions, generating a total of 1440000 data records. Utilizing these simulated data, we design and conduct comparative experiments between models as well as data types. The results demonstrate that both the GraphResLSTM model and road segment average speed data outperform other models and data types notably in OD prediction tasks.

Early disease detection is crucial for maximizingcrop yields and minimizing financial losses in agriculture. Inorder to categorise leaf diseases in pepper, tomato, and potato plants, this study suggests a revolutionary CNN design. The algorithm collects disease-specific features from input photos by using data augmentation techniques to artificially enlarge the training dataset. ReLU-activated convolutional layers gradually capture features at different levels, from low to high, while max pooling layers minimise spatial dimensionality. After thecharacteristics are extracted, a fully-connected layers with a softmax activation function classify them into illness groups. A well chosen dataset containing labelled healthy and sick leaves is used to train and validate the model. Generalizability to untesteddata is ensured via performance evaluation on an independent testing set. The field of deep learning for agricultural applications benefits from this research. This strategy has the ability to rev- olutionise agricultural practices by enabling automated disease identification. This might result in early interventions, better crop health, and eventually sustainable agricultural production.

Deep learning has increasingly been employed to identify minerals. However, deep learning can only be used to identify minerals in the distribution of the training set, while any mineral outside the spectrum of the training set is inevitably categorized erroneously within a predetermined class from the training set. To solve this problem, the study introduces the approach that amalgamates One-Class Support Vector Machines (OCSVM) with the ResNet architecture for the out-of-distribution mineral detection. Initially, ResNet undergoes training using a training set comprising well-defined minerals. Subsequently, the earlier layers of the trained ResNet are employed to extract the discriminative features of the mineral under consideration. These extracted mineral features then become the input for OCSVM. When OCSVM discerns the mineral in the training set's distribution, it triggers the subsequent layers within the trained ResNet, facilitating the accurate classification of the mineral into one of the predefined categories encompassing the known minerals. In the event OCSVM identifies the mineral out of the training set's distribution, it is unequivocally categorized as an unclassified or 'unknown' mineral. Empirical results substantiate the method's capability to identify out-of-distribution minerals while concurrently maintaining a commendably high accuracy rate for the classification of the 36 in-distribution minerals.

Unmanned Underwater Vehicles (UUVs) are pivotal in ocean exploration, research, and various industrial activities such as marine mining and offshore engineering. However, traditional methods of navigating these vehicles face significant challenges, mainly due to the inefficacy of electromagnetic waves in water, leading to signal loss. To address these limitations, researchers are increasingly turned learning, an artificial intelligence technique capable of learning from data-enhancing underwater navigation, mainly through visual Simultaneous Localization and Mapping (SLAM). This paper explores integrating deep learning methodologies and sensor technologies to revolutionize underwater navigation for UUVs. Proprioceptive sensors, along with exteroceptive sensors, are crucial in accurately measuring and comprehending the underwater environment. Additionally, the paper provides detailed insights into the processes of underwater SLAM, camera-based underwater positioning systems, sonar systems for underwater navigation, and the utilization of Lidar in underwater navigation. Furthermore, it delves into applying deep learning techniques in underwater SLAM, offering a comprehensive understanding of the innovative processes driving advancements in underwater vehicle navigation. By leveraging these advancements, this research aims to improve underwater navigation systems' precision, reliability, and adaptability, thereby unlocking new frontiers in ocean exploration and industrial applications for UUVs.

All types of sports are potential application scenarios for automatic and real-time visual object and event detection. In rink hockey, the popular roller quad skate variant of hockey team sports, it is of great interest to automatically track player’s movements and positions, player’s sticks and, also, making other judgments, such as being able to locate the ball. In this work, we introduce a real-time pipeline composed by an object detection model, created specifically for rink hockey games, followed by a knowledge-based event detection module. Even in the presence of occlusions and quick motions, our deep learning object detection model effectively identifies and tracks, in real-time, important visual elements such as: ball; players; sticks; referees; crowd; goalkeeper; and goal. Using a curated dataset composed by a collection of videos of rink hockey, comprising 2525 annotated frames, we trained and evaluated the algorithm performance and compare it to state of the art object detection techniques. Our object detection model, based on YOLOv7, presents a global accuracy of 80%, and presents a good performance in terms of accuracy and speed, according to our results, making it a good choice for rink hockey applications. In our initial tests, the event detection module successfully detected one important event type in rink hockey games, the occurrence of penalties.

The accurate state of health (SOH) estimation of lithium-ion batteries (LIBs) during operation is crucial to ensure optimal performance, prolonging battery life and preventing unexpected failure or safety hazards. This work presents a storage and performance optimised deep learning approach to predict the capacity based SOH of LIBs using raw sensor data from partial charging curves under constant current condition. The proposed model is based on a combination of a 1-dimensional convolutional and long-short term memory neural network and processes time, voltage and incremental capacity of partial charging curves as time series. The model is cross-validated on different aging scenarios reaching an overall MAE = 0.418% and RMSE = 0.531%, promising an accurate SOH estimation of LIBs under varying usage and environmental conditions in a real world application.

The importance of detecting and diagnosing the imminence of aneurysm rupture before it occurs cannot be overstated. However, this process is often time-consuming and challenging, with variability in conclusions not uncommon among experts. Furthermore, current state-of-the-art models in medical image segmentation suffer from limited availability of large annotated datasets for training, exacerbated by an immense data imbalance. In most segmentation tasks, 3D segmentation is preferred due to its capacity to leverage more contextual information. However, these models require more data, which is constrained by the aforementioned issues. In the realm of current diagnosis models, those lacking geographic context are notably ineffective. To address these issues, the aim is to develop a model pipeline to accurately detect cerebral intracranial aneurysms and diagnose rupture imminence through 3D magnetic resonance angiography (MRA) and tabular input, augmented with the implementation of neuro-symbolic ai. The utilization of data fusion to tackle the lack of context in tabular models is proposed, leveraging extracted geographical features from a segmentation model. To enhance segmentation results and tackle the data imbalance in aneurysm segmentation, a two-stage model pipeline that extracts contextual geographic features before aneurysm segmentation is suggested. Segmentation results are additionally improved through ensemble techniques and novel preprocessing techniques. Finally, a neuro-symbolic aspect is introduced to enhance model diagnosis, interpretability and performance. The multi-step Integrated Neuro-Symbolic Analysis Pipeline for Cerebral Aneurysm Rupture Diagnosis is introduced.

Hybrid forecasting methods have emerged as a solution surpassing the limitations of both statistical and deep learning approaches. While the first emphasize the significance of variables, they often produce worse forecasting results when compared to newer techniques. In contrast, deep learning models remain enigmatic "black boxes" in terms of interpretability, although achieving better results in forecasting. This article introduces the Comprehensive Cross-Correlation and Lagged Linear Regression Deep Learning (CCLR-DL) framework, designed to harness the best of both approaches, enhancing forecasting accuracy while retaining model interpretability through a feature selection process. CCLR-DL blens cross-correlation analysis, lagged multiple linear regression and granger's causality procedures with deep learning architectures based on LSTM. In a practical demonstration, CCLR-DL was applied to a real database of clinical visits associated to diagnoses in Catalonia, Spain (tracking a population of 6.3 million patients during 10 years). Predicting visits enables the healthcare managers to be ready for future demand shifts. Results demonstrate a consistent and substantial improvement over standalone statistical and deep learning methods when predicting healthcare demand. This hybrid approach not only showcases its efficacy but also offers a promising solution to the challenge of balancing predictive accuracy with model explicability. In this context, this work aims to design and validate a method for feature selection and forecasting of multivariate high dimensional time series datasets not only to improve prediction accuracy but also to model transparency by identifying a subset of variables that improve predictions and G-cause the target variable.

The new energy structure needs to balance energy security and dual carbon goals, which has brought major challenges to coal-fired power plants, the pollution reduction and carbon emissions reduction of coal-fired power plants will be a key task in the future. This article proposes an optimization operation of electrostatic precipitators(ESP), based on the working mechanism and historical data of ESP, voltage-current characteristic model and outlet dust concentration prediction model are constructed by deep learning algorithm, Particle Swarm Optimization(PSO) is used to achieve the optimal energy consumption while ensuring stable outlet dust concentration. By training with historical data collected on site, accurate prediction of secondary current and outlet dust concentration of ESP has been achieved, the Mean Absolute Percentage Error(MAPE) of secondary current is less than 1.5%, and the MAPE of outlet dust concentration of ESP on the test set is less than 5.2%. Finally, the optimization experiment is carried out in a 330MW coal-fired power plants, the results showed that the fluctuation of the outlet dust concentration is more stable, and the energy saving is about 43% after optimization, according to the annual operation of 300 days, the annual average carbon reduction is approximately 2621.34 tons. This method is effective and can be applied widely.

The integration of Artificial Intelligence (AI) with Digital Twins (DTs) has emerged as a promising approach to revolutionize healthcare, particularly in the diagnosis and management of thoracic disorders. This study proposes a comprehensive framework, named Lung-DT, which leverages IoT sensors and AI algorithms to establish a digital representation of a patient’s respiratory health. Using the YOLOv8 neural network, the Lung-DT system accurately classifies chest X-Rays into five distinct categories of lung diseases, including "Normal," "Covid," "Lung Opacity," "Pneumonia," and "Tuberculosis". The system’s performance was evaluated on a chest X-Ray dataset, demonstrating an impressive average accuracy of 96.6% across all classes. Further tests (prediction) were conducted on the trained network using a third dataset available in the literature and completely unknown to the network, yielding an average accuracy of 98% across three classes. The proposed Lung-DT framework offers several advantages over conventional diagnostic methods. Firstly, it enables real-time monitoring of lung health through continuous data acquisition from IoT sensors, facilitating early diagnosis and intervention. Secondly, the AI-powered classification module provides automated and objective assessments of chest X-Rays, reducing dependence on subjective human interpretation. Thirdly, the twin digital representation of the patient’s respiratory health allows for comprehensive analysis and correlation of multiple data streams, providing valuable insights for personalized treatment plans. The integration of IoT sensors, AI algorithms, and DT technology within the Lung-DT system demonstrates a significant step towards improving thoracic healthcare. By enabling continuous monitoring, automated diagnosis, and comprehensive data analysis, the Lung-DT framework has enormous potential to enhance patient outcomes, reduce healthcare costs, and optimize resource allocation.

Building deep learning models proposed by third parties can become a simple task when specialized libraries are used. However, a great deal of mystery still surrounds the design of new models or the modification of existing ones. These tasks require in-depth knowledge of the different components or building blocks as well as their dimensions. This information is limited and broken up in different literature. In this article, we collect and explain in-depth the building blocks to design deep learning models, starting from the artificial neuron to the concepts involved in building deep neural networks. Furthermore, the implementation of each building block is exemplified using the Keras library.

Industrial radiography is a pivotal non-destructive testing (NDT) method that ensures quality and safety in a wide range of industrial sectors. Conventional human-based approaches, however, are prone to challenges in defect detection accuracy and efficiency, primarily due to the high inspection demand from manufacturing industries with high production throughput. To solve this challenge, numerous computer-based alternatives have been developed, including Auto-mated Defect Recognition (ADR) using deep learning algorithms. At the core of training, these algorithms demand large volumes of data that should be representative of real-world cases. However, the availability of digital X-ray radiography data for open research is limited by non-disclosure contractual terms in the industry. This study presents a pipeline that is capable of modeling synthetic images based on statistical information acquired from X-ray intensity distribution from real digital X-ray radiography images. Through meticulous analysis of the intensity distribution in digital X-ray images, the unique statistical patterns associated with the exposure conditions used during image acquisition, type of component, thickness variations, beam divergence, anode heel effect, etc., are extracted. The realized synthetic images were utilized to train deep learning models, yielding an impressive model performance with mean intersection over union (IoU) of 0.93, and mean dice coefficient of 0.96, on real unseen digital X-ray radiography images. This methodology is scalable and adaptable, making it suitable for diverse industrial applications.

Text classification is one of the most important task in natural language processing, In this research, we carried out several experimental research on three (3) of the most popular Text classification NLP classifier in Convolutional Neural Network (CNN), Multinomial Naive Bayes (MNB), and Support Vector Machine (SVN). In the presence of enough training data, Deep Learning CNN works best in all parameters for evaluation with 77% accuracy, followed by SVM with accuracy of 76%, and multinomial Bayes with least performance of 69% accuracy. CNN has the best performance in the presence of large enough training dataset because of the presence of filter/ kernels which help to indentify patterns in text data regardless of their position in the sentence. We repeated the training again with just one-third of our data, at this point SVM comes with the best performance, the performance of CNN noticeably drops but still better than Multinomial Naive Bayes, the reason why SVM works best when we reduce the training data was because of its ability to look for a hyper-plane that creates a boundary between different classes of data so as to properly classify them, so we believed that getting the hyper-plane was more efficient when we reduce the dataset, hence reason for the good performance. Multinomial Naive Bayes have the least performance which we attributed to its assumption of independency between the features which sometimes does not hold true. We concluded that availability of data should be an important factor when choosing classifier for Natural Language Processing Text Classification task. CNN should be use in the presence of enough dataset, and SVM should be use when data is not enough. Multinomial Naive Bayes must not be trusted with state of the art NLP task due to its assumption of independency between the features.

The escalation of climate change and the increasing frequency of extreme weather events have amplified the importance of precise and timely lightning prediction. This predictive capability is pivotal for the preservation of life, protection of property, and maintenance of crucial infrastructure safety. Recently, the rapid advancement and successful application of data-driven deep learning across diverse sectors, particularly in computer vision and spatio-temporal data analysis, have opened up innovative avenues for enhancing both the accuracy and efficiency of lightning prediction. This article presents a comprehensive review of the broad spectrum of existing lightning prediction methodologies. Starting from traditional numerical forecasting techniques, we traverse the path to the most recent breakthroughs in deep learning research. We encapsulate these diverse methods, shedding light on their progression and summarizing their capabilities, while also predicting their future development trajectories. This exploration is designed to enhance our understanding of these methodologies, allowing us to better utilize their strengths, navigate their limitations, and potentially integrate these techniques to create novel and powerful lightning prediction tools. Through such endeavors, our aim is to bolster our preparedness against the growing unpredictability of our climate and ensure a proactive stance towards lightning prediction.

AK is a common precancerous skin condition that requires effective detection and treatment monitoring. To improve the monitoring of AK burden in clinical settings with enhanced automation and precision, the present study evaluates the application of semantic segmentation based on the U-Net architecture (AKU-Net). AKU-Net employs transfer learning to compensate for the relatively small dataset of annotated images and integrates a recurrent process based on convLSTM to exploit contextual information and address the challenges related to low contrast and ambiguous boundaries of AK-affected skin regions. We used an annotated dataset of 569 clinical photographs from 115 patients with actinic keratosis to train and evaluate the model. From each photograph, patches of 512x512 pixels were extracted using translation lesion boxes that encompass lesions in different positions and capture different contexts of perilesional skin. In total, 16488 translation augmented crops were used for training the model, and 403 lesion center crops were used for testing. To demonstrate the improvements in AK detection, AKU-net was compared with plain U-Net and U-Net++ architectures. The experimental results highlighted the effectiveness of AKU-Net, improving both automation and precision over existing approaches, paving the way for more effective and reliable evaluation of actinic keratosis in clinical settings.

Data-driven models (DDMs) are extensively used in environmental modeling but face challenges due to limited training data and potential results not adhering to physical laws. To address this challenge, this study developed a process-guided deep learning (PGDL) model, integrating a long short-term memory (LSTM) neural network and a process-based model (PBM), CE-QUAL-W2 (W2), to predict water temperature in a stratified reservoir. The PGDL included an energy constraint term from W2's thermal energy equilibrium into the cost function of the LSTM, besides the mean square error term. In PGDL, parameters were optimized by penalizing deviations from the energy law, ensuring adherence to physical constraints. Compared to LSTM, PGDL demonstrated enhanced satisfaction with the energy balance and superior performance in water temperature prediction. Even with less field data for training, PGDL outperformed both LSTM and calibrated W2 after pre-training with data generated using the uncalibrated W2. Therefore, integration of DDM with a PBM ensured physical consistency in water temperature prediction for complex stratified reservoirs with limited data. Moreover, pre-training the PGDL with PBM proved highly effective in mitigating bias and variance due to insufficient field measurement data.

There is a need for cost-effective and non-invasive methods of monitoring feeding behavior in livestock operations, considering the significant impact of feed costs on economic efficiency and assisting in detecting health issues of group-fed animals. This paper proposes using deep learning-based computer vision techniques to detect pen-fed beef cattle feeding behavior using Mask Region-based Convolutional Neural Network (RCNN). A deep learning model was pre-trained on the Common Objects in Context (COCO) dataset to generate cattle instance segmentation. Manually defined feed bunk polygons are compared with these segmentation masks to derive feeding time for each bunk. A full day’s worth of video data and the corresponding physical sensor data are collected for the experiment. By benchmarking the computer vision detected data with physical ground truth over random time segments from morning to evening (thus various lighting conditions), the optimal thresholds for Mask RCNN are determined to be 0.7 for bounding boxes and 0.1 for masks. Using these parameters. The reports suggest that the computer vision system achieved a precision of 87.2% and a recall of 89.1%, signifying precise detection of feeding events. Our study, to the best of our knowledge, was one of the first investigations of instance segmentation on feeding time sense, which combines deep learning methods with traditional computer vision logistics, reporting on feeding time data collection and processing, camera testing and adjustment, and performance evaluation. Future research directions include computer vision applied in feed grading and animal re-identification for individual production analysis.

With metal oxide semiconductors being a promising candidate for accurate indoor air quality assessments, multiple drawbacks of the gas sensors prevent their widespread use. Examples include poor selectivity, instability over time, and sensor poisoning. Complex calibration methods and advanced operation modes can solve some of those drawbacks. However, this leads to long calibration times, which are unsuitable for mass production. In recent years, multiple attempts to solve calibration transfer have been made with the help of direct standardization, orthogonal signal correction, and many more methods. Besides those, a new promising approach is transfer learning from deep learning. This article will compare different calibration transfer methods, including direct standardization, piecewise direct standardization, transfer learning for deep learning models, and global model building. The machine learning methods to calibrate the initial models for calibration transfer are feature extraction, selection, and regression (established methods) and a custom convolutional neural network TCOCNN. It is shown that transfer learning can outperform the other calibration transfer methods regarding the root mean squared error, especially if the initial model is built with multiple sensors. It was possible to reduce the number of calibration samples by up to 99.3 % (from 10 days to approximately 2 hours) and still achieve an RMSE for acetone of around 18 ppb (15 ppb with extended individual calibration) if six different sensors were used for building the initial model. Furthermore, it was shown that the other calibration transfer methods (direct standardization and piecewise direct standardization) also work reasonably well for both machine learning approaches, primarily when multiple sensors are used for the initial model.

AVs suffer reduced maneuverability and performance due to the degradation in sensor performances in fog. Such degradation causes significant object detection errors essential for AVs' safety-critical conditions. For instance, YOLOv5 performs significantly well under favorable weather but suffers miss detections and false positives due to atmospheric scattering caused by fog particles. Existing deep object detection techniques often exhibit a high degree of accuracy. The drawback is being sluggish at object detection in fog. Object detection methods with fast detection speed have been obtained using deep learning at the expense of accuracy. The problem of the lack of balance between detection speed and accuracy in fog persist. This paper presents an improved YOLOv5-based multi-sensor fusion network that combines radar's object detection with a camera image bounding box. We transformed radar detection by mapping the radar detections into a two-dimensional image coordinate and projected the resultant radar image on the camera image. Using the attention mechanism, we emphasized and improved important feature representation used for object detection while reducing high-level feature information loss. We trained and tested our multi-sensor fusion network on clear and multi-fog weather datasets obtained from the CARLA simulator. Our result shows that the proposed method significantly enhances the detection of distant and small objects. Our small CR-YOLOnet model best strikes a balance between accuracy and speed with an accuracy of 0.849 at 69 fps.

World Health Organization (WHO) has announced the monkeypox (MPX) epidemic a global public health emergency due to its re-emergence, remarkable increase in the number of MPX cases worldwide, and its potential spread. This paper introduces the symptoms, complications, and features of MPX; its transmission, diagnosis and testing, vaccines and treatment; MPX and sexually transmitted diseases, especially the human immunodeficiency virus (HIV); possible natural hosts or reservoirs of the monkeypox virus (MPXV). A useful tool for MPX and surgical safety recommendations are presented. The challenges in fighting the MPX epidemic, One Health strategy, and future research are discussed.

Automated lip reading is a research problem that has developed considerably in recent years. Lip reading is evaluated both visually and audibly in some cases. The lip reading model is a field of use for detecting specific words using images from security cameras, but it is not possible to use audio-visual databases in this situation. It is not possible to obtain the sound input of the pronounced word in all cases. We collected a new Turkish dataset with only the image in this study. The new dataset is produced using Youtube videos, which is an uncontrolled environment. For this reason, images have difficult parameters in terms of environmental factors such as light, angle, color, and personal characteristics of the face. Despite the different features on the human face such as mustache, beard, and make-up, the visual speech recognition problem was developed on 10 classes including single words and two-word phrases using Convolutional Neural Networks (CNN) without any intervention on the data. The proposed study using only-visual data obtained a model which is automated visual speech recognition with a deep learning approach. In addition, since this study uses only-visual data, the computational cost and resource usage is less than in multi-modal studies. It is also the first known study to address the lip reading problem with a deep learning algorithm using a new dataset belonging to the Ural-Altaic languages.

In response to the growing inspection demand exerted by process automation in component manufacturing, Non-destructive testing (NDT) continues to explore automated approaches that utilize deep learning algorithms for defect identification, including within digital X-ray radiography images. This necessitates a thorough understanding of the implication of image quality parameters on the performance of these deep learning models. This study investigates the influence of two image quality parameters, namely Signal-to-Noise Ratio (SNR) and Contrast-to-Noise Ratio (CNR), on the performance of U-net deep learning segmentation model. Input images were acquired with varying combinations of exposure factors such as kilovoltage, milli-ampere, and exposure time, which altered the resultant quality. The data was sorted into 5 different datasets according to their measured SNR and CNR values. The deep learning model was trained 5 distinct times, utilizing a unique dataset for each training session. Training the model with high CNR values yielded an intersection over Union (IoU) metric of 0.9594 on test data of the same category but drops to 0.5875 when tested on lower CNR test data. The result in this study emphasizes the importance of achieving a balance in training dataset according to the investigated quality parameters, to enhance the performance of deep learning segmentation models in NDT radiography applications.

Artificial intelligence’s rapid advancement has enabled various applications, including intelligent video surveillance systems, assisted living, and human-computer interaction. These applications often require one core task: video-based human action recognition. Research in human video-based human action recognition is vast and ongoing, making it difficult to assess the full scope of available methods and current trends. This survey provides an in-depth exploration of the vision-based human action recognition field, comprehensively offering the available techniques and their evolution, highlighting the cutting-edge ideas driving its development. We also analyze the most used keywords in research papers over the past years to identify trends and predict possible future directions. Hence, this concise survey helps researchers understand the breadth of existing approaches, evaluate current research trends, and stay up-to-date on potential developments.

Schistosomiasis is a debilitating parasitic disease of poverty that affects more than 200 million people worldwide, mostly in sub-Saharan Africa, and is clearly associated with the construction of dams and water resource management infrastructure in tropical and subtropical areas. Changes to hydrology and salinity linked to water infrastructure development may create conditions favorable to the aquatic vegetation that is suitable habitat for the intermediate snail hosts of schistosome parasites. With thousands of small and large water reservoirs, irrigation canals, and dams developed or under construction in Africa, it is crucial to accurately assess the spatial distribution of high-risk environments that are habitat for freshwater snail intermediate hosts of schistosomiasis in rapidly changing ecosystems. Yet, standard techniques for monitoring snails are labor-intensive, time-consuming, and provide information limited to the small areas that can be manually sampled. Consequently, in low-income countries where schistosomiasis control is most needed, there are formidable challenges to identify potential transmission hotspots for targeted medical and environmental interventions. In this study, we developed a new framework to map the spatial distribution of suitable snail habitat across large spatial scales in the Senegal River Basin by integrating satellite data, high-definition, low-cost drone imagery, and an artificial intelligence (AI)-powered computer vision technique called semantic segmentation. A deep learning model (U-Net) was built to automatically analyze high-resolution satellite imagery to produce segmentation maps of aquatic vegetation, with a fast and robust generalized prediction that proved more accurate than a more commonly used random forest approach. Accurate and up-to-date knowledge of areas at highest risk for disease transmission can increase the effectiveness of control interventions by targeting habitat of disease-carrying snails. With the deployment of this new framework, local governments or health actors might better target environmental interventions to where and when they are most needed in an integrated effort to reach the goal of schistosomiasis elimination.

：An effective technology for predicting the end-point phosphorous content of basic oxygen furnace (BOF) can provide theoretical instruction to improve the quality of steel via controlling the hardness and toughness. Given the slightly inadequate prediction accuracy in the existing prediction model, a novel hybrid method was suggested to more accurately predict the end-point phosphorus content by integrating an enhanced sparrow search algorithm (ESSA) and a multi-strategy with a deep extreme learning machine (DELM) as ESSA-DELM in this study. To begin with, the input weights and hidden biases of DELM were randomly selected, resulting in that DELM inevitably had a set of non-optimal or unnecessary weights and biases. Therefore, the ESSA was used to optimize the DELM in this work. For the ESSA, the Trigonometric substitution mechanism and Cauchy mutation were introduced to avoid trapping in local optima and improve the global exploration capacity in SSA. Finally, to evaluate the prediction efficiency of ESSSA-DELM, the proposed model was tested on process data of the converter from the Baogang steel plant. The efficacy of ESSA-DELM was more superior to that of other DELM-based hybrid prediction models and conventional models. The result demonstrated that the hit rate of end-point phosphorus content within ±0.003%, ±0.002%, and ±0.001% was 91.67%, 83.33%, and 63.55%, respectively. The proposed ESSA-DELM model could possess better prediction accuracy compared with other models, which could guide field operations.

Software reliability is an important characteristic for ensuring the qualities of software products. Predicting the potential number of bugs from the beginning of a development project allows practitioners to make the appropriate decisions regarding testing activities. In the initial development phases, applying traditional software reliability growth models (SRGMs) with limited past data does not always provide reliable prediction result for decision making. To overcome this, herein we propose a new software reliability modeling method called deep cross-project software reliability growth model (DC-SRGM). DC-SRGM is a cross-project prediction method that uses features of previous projects’ data through project similarity. Specifically, the proposed method applies cluster-based project selection for training data source and modeling by a deep learning method. Experiments involving 15 real datasets from a company and 11 open source software datasets show that DC-SRGM can more precisely describe the reliability of ongoing development projects than existing traditional SRGMs and the LSTM model.

Deep learning (DL), which is originated from an artificial neural network (ANN), is one of the major technologies of today's smart cybersecurity systems or policies to function in an intelligent manner. Popular deep learning techniques, such as Multi-layer Perceptron (MLP), Convolutional Neural Network (CNN or ConvNet), Recurrent Neural Network (RNN) or Long Short-Term Memory (LSTM), Self-organizing Map (SOM), Auto-Encoder (AE), Restricted Boltzmann Machine (RBM), Deep Belief Networks (DBN), Generative Adversarial Network (GAN), Deep Transfer Learning (DTL or Deep TL), Deep Reinforcement Learning (DRL or Deep RL), or their ensembles and hybrid approaches can be used to intelligently tackle the diverse cybersecurity issues. In this paper, we aim to present a comprehensive overview from the perspective of these neural networks and deep learning techniques according to today's diverse needs. We also discuss the applicability of these techniques in various cybersecurity tasks such as intrusion detection, identification of malware or botnets, phishing, predicting cyber-attacks, e.g. denial of service (DoS), fraud detection or cyber-anomalies, etc. Finally, we highlight several research issues and future directions within the scope of our study in the field. Overall, the ultimate goal of this paper is to serve as a reference point and guidelines for the academia and professionals in the cyber industries, especially from the deep learning point of view.

Estimating the remaining useful life (RUL) of components is a crucial task to enhance the reliability, safety, productivity, and to reduce maintenance cost. In general, predicting the RUL of a component includes constructing a health indicator ( ) to infer the current condition of the component, and modelling the degradation process, to estimate the future behavior. Although many signal processing and data-driven based methods were proposed to construct the , most of the existing methods are based on manual feature extraction techniques, and need the prior knowledge of experts, or rely on a large amount of failure data. Therefore, in this study, a new data-driven method based on the convolutional autoencoder (CAE) is presented to construct the . For this purpose, the continuous wavelet transform (CWT) technique is used to convert the raw acquired vibrational signals into a two-dimensional image; then, the CAE model is trained by the healthy operation dataset. Finally, the Mahalanobis Distance (MD) between the healthy and failure stages is measured as the . The proposed method is tested on a benchmark bearing dataset and compared with several other traditional construction models. Experimental results indicate that the constructed exhibits a monotonically increasing degradation trend and has a good performance to detect incipient faults.

Soybean maturity is a trait of critical importance for the development of new soybean cultivars, nevertheless, its characterization based on visual ratings has many challenges. Unmanned aerial vehicles (UAVs) imagery-based high-throughput phenotyping methodologies have been proposed as an alternative to the traditional visual ratings of pod senescence. However, the lack of scalable and accurate methods to extract the desired information from the images remains a significant bottleneck in breeding programs. The objective of this study was to develop an image-based high-throughput phenotyping system for evaluating soybean maturity in breeding programs. Images were acquired twice a week, starting when the earlier lines began maturation until the latest ones were mature. Two complementary convolutional neural networks (CNN) were developed to predict the maturity date. The first using a single date and the second using the five best image dates identified by the first model. The proposed CNN architecture was validated using more than 15,000 ground truth observations from five trials, including data from three growing seasons and two countries. The trained model showed good generalization capability with a root mean squared error lower than two days in four out of five trials. Four methods of estimating prediction uncertainty showed potential at identifying different sources of errors in the maturity date predictions. The architecture used solves limitations of previous research and can be used at scale in commercial breeding programs.

Aluminum profile surface defects can greatly affect the performance, safety and reliability of products. Traditional human-based visual inspection is low accuracy and time consuming, and machine vision-based methods depend on hand-crafted features which need to be carefully designed and lack robustness. To recognize the multiple types of defects with various size on aluminum profiles, a multiscale defect detection network based on deep learning is proposed. Then, the network is trained and evaluated using aluminum profile surface defects images. Results show 84.6%, 48.5%, 96.9%, 97.9%, 96.9%, 42.5%, 47.2%, 100%, 100%, 43.3% average precision(AP) for the ten defect categories, respectively, with a mean AP of 75.8%, which illustrate the effectiveness of the network in aluminum profile surface defects detection. In addition, saliency maps also show the feasibility of the proposed network.

The detection of seismic events at regional and teleseismic distances is critical to Nuclear Treaty Monitoring. Traditionally, detecting regional and teleseismic events has required the use of an expensive multi-instrument seismic array; however in this work, we present DeepPick, a novel seismic detection algorithm capable of array-like performance from a single trace. We achieve this directly, by training our single-trace detector against labeled events from an array catalog, and by utilizing a deep temporal convolutional neural network. The training data consists of all arrivals in the International Seismological Centre Catalog for seven seismic arrays over a five year window from 1 Jan 2010 to 1 Jan 2015, yielding a total training set of 608,362 detections. The test set consists of the same seven arrays over a one year window from 1 Jan 2015 to 1 Jan 2016. We report our results by training the algorithm on six of the arrays and testing it on the seventh, so as to demonstrate the transportability and generalization of the technique to new stations. Detection performance against this test set is outstanding. Fixing a type-I error rate of 1%, the algorithm achieves an overall recall rate of 73% on the 141,095 array beam picks in the test set, yielding 102,394 correct detections. This is more than 4 times the 23,259 detections found in the analyst-reviewed single-trace catalogs over the same period, and represents an 8dB improvement in detector sensitivity over current methods. These results demonstrate the potential of our algorithm to significantly enhance the effectiveness of the global treaty monitoring network.

The violation of data integrity in automotive Cyber-Physical Systems (CPS) may lead to dangerous situations for drivers and pedestrians in terms of safety. In particular, cyber-attacks on the sensor could easily degrade data accuracy and consistency over any other attack, we investigate attack detection and identification based on a deep learning technology on wheel speed sensors of automotive CPS. For faster recovery of a physical system with detection of the cyber-attacks, estimation of a specific value is conducted to substitute false data. To the best of our knowledge, there has not been a case of joining sensor attack detection and vehicle speed estimation in existing literatures. In this work, we design a novel method to combine attack detection and identification, vehicle speed estimation of wheel speed sensors to improve the safety of CPS even under the attacks. First, we define states of the sensors based on the cases of attacks that can occur in the sensors. Second, Recurrent Neural Network (RNN) is applied to detect and identify wheel speed sensor attacks. Third, in order to estimate the vehicle speeds accurately, we employ Weighted Average (WA), as one of the fusion algorithms, in order to assign a different weight to each sensor. Since environment uncertainty while driving has an impact on different characteristics of vehicles and cause performance degradation, the recovery mechanism needs the ability adaptive to changing environments. Therefore, we estimate the vehicle speeds after assigning a different weight to each sensor depending on driving situations classified by analyzing driving data. Experiments including training, validation, and test are carried out with actual measurements obtained while driving on the real road. In case of the fault detection and identification, classification accuracy is evaluated. Mean Squared Error (MSE) is calculated to verify that the speed is estimated accurately. The classification accuracy about test additive attack data is 99.4978%. MSE of our proposed speed estimation algorithm is 1.7786. It is about 0.2 lower than MSEs of other algorithms. We demonstrate that our system maintains data integrity well and is safe relatively in comparison with systems which apply other algorithms.

Non-invasive, electroencephalography (EEG)-based brain-computer interfaces (BCIs) on motor imagery movements translate the subject’s motor intention into control signals through classifying the EEG patterns caused by different imagination tasks, e.g. hand movements. This type of BCI has been widely studied and used as an alternative mode of communication and environmental control for disabled patients, such as those suffering from a brainstem stroke or a spinal cord injury (SCI). Notwithstanding the success of traditional machine learning methods in classifying EEG signals, these methods still rely on hand-crafted features. The extraction of such features is a difficult task due to the high non-stationarity of EEG signals, which is a major cause for the stagnating progress in classification performance. Remarkable advances in deep learning methods allow end-to-end learning without any feature engineering, which could benefit BCI motor imagery applications. We developed three deep learning models: 1) a long short-term memory (LSTM); 2) a proposed spectrogram-based convolutional neural network model (pCNN); and 3) a recurrent convolutional neural network (RCNN), for decoding motor imagery movements directly from raw EEG signals without (manual) feature engineering. Results were evaluated on our own, publicly available, EEG data collected from 20 subjects and on an existing dataset known as 2b EEG dataset from "BCI Competition IV". Overall, better classification performance was achieved with deep learning models compared to state-of-the art machine learning techniques, which could chart a route ahead for developing new robust techniques for EEG signal decoding. We underpin this point by demonstrating the successful real-time control of a robotic arm using our CNN based BCI.

Vibration measurement serves as the basis for various engineering practices such as natural frequency or resonant frequency estimation. As image acquisition devices become cheaper and faster, vibration measurement and frequency estimation through image sequence analysis continue to receive increasing attention. In the conventional photogrammetry and optical methods of frequency measurement, vibration signals are first extracted before implementing the vibration frequency analysis algorithm. In this work, we demonstrated that frequency prediction can be achieved using a single feed-forward convolutional neural network. The proposed method is verified using a vibration signal generator and excitation system, and the result obtained was compared with that of an industrial contact vibrometer in a real application. Our experimental results demonstrate that the proposed method can achieve acceptable prediction accuracy even in unfavorable field conditions.

Synesthesia is a psychological phenomenon where sensory signals become mixed. Input to one sensory modality produces an experience in a second, unstimulated modality. In “grapheme-color synesthesia”, viewed letters and numbers evoke mental imagery of colors. The study of this condition has implications for increasing our understanding of brain architecture and function, language, memory and semantics, and the nature of consciousness. In this work, we propose a novel application deep learning to model perception in grapheme-color synesthesia. Achromatic letter images, taken from database of handwritten characters, are used to induce synesthesia. Results show the model learns to accurately create a colored version of the inducing stimulus, according to a statistical distribution from experiments on a sample population of grapheme-color synesthetes. The spontaneous, creative mental imagery characteristic of the synesthetic perceptual experience is reproduced by the model. A model of synesthesia that generates testable predictions on brain activity and behavior is needed to complement large scale data collection efforts in neuroscience, especially when articulating simple descriptions of cause (stimulus) and effect (behavior). The research and modeling approach reported here begins to address this need.

Developing new antibiotics poses a significant challenge in the fight against antimicrobial resistance (AMR), a critical global health threat responsible for approximately 5 million deaths annually. Finding new classes of antibiotics that are safe, have acceptable pharmacokinetic properties, and are appropriately active against pathogens is a lengthy and expensive process. Therefore, high-throughput platforms are needed to screen large libraries of synthetic and natural compounds. In this review, we present bacterial cytological profiling (BCP) as a rapid, scalable, and cost-effective method for identifying the mechanisms of action of antibiotics, offering a promising tool for combating AMR and drug discovery. We present the application of BCP for different bacterial organisms and different classes of antibiotics and discuss BCP's advantages, limitations, and potential improvements. Furthermore, we highlight the studies that have utilized BCP to investigate pathogens listed in the Bacterial Priority Pathogens List 2024 and we identify the pathogens whose cytological profiles are missing. Lastly, we explore the most recent artificial intelligence and deep learning techniques that could enhance the analysis of data generated by BCP, potentially advancing our understanding of antibiotic resistance mechanisms and the discovery of novel druggable pathways.

Abstract: The future of transportation is being reshaped by autonomous vehicles (AVs), which promise to revolutionize road safety, accessibility, and environmental sustainability. Central to their evolution are advancements in artificial intelligence (AI), which enable real-time perception, decision-making, and control. This paper explores the future trajectory of AI in AVs, highlighting innovative AI paradigms such as explainable AI, federated learning, and adaptive regulatory frameworks. It delves into the development of sophisticated perception algorithms for environmental understanding, advanced decision-making systems employing reinforcement learning and deep neural networks, and precise control mechanisms through predictive modeling and optimization. By addressing current challenges, including regulatory hurdles and the complexity of AI algorithms, this paper provides a comprehensive outlook on the potential and implications of AV technology. It envisions a future where AI-driven AVs are seamlessly integrated into society, offering profound insights into their impact on transportation and societal dynamics.

This paper describes a Long Short-Term Memory (LSTM) neural network model used to simulate the dynamics of the OC3 reference design of a Floating Offshore Wind Turbine Spar unit. It crafts an advanced neural network with an encoder-decoder architecture capable of predicting the Spar’s motion and fairlead tensions time series. These predictions are based on wind and wave excitations across various operational and extreme conditions. The LSTM network, trained on an extensive dataset from over 300 fully coupled simulation scenarios using OpenFAST, ensures a robust framework that captures the complex dynamics of floating platform under diverse environmental scenarios. This framework’s effectiveness is further verified by thoroughly evaluating the model’s performance, leveraging comparative statistics and accuracy assessments to highlight its reliability. This methodology contributes to substantial reductions in computational time. This research aims to provide critical insights that facilitate the optimization of offshore wind turbines, marking a step forward in the quest for more efficient and dependable renewable energy solutions.

As digital communication becomes increasingly integral to personal and corporate activities, phishing attacks have emerged as a prevalent threat, ingeniously mimicking legitimate sources to illicitly acquire sensitive information. This research paper details the development of a sophisticated phishing detection application utilizing the DistilBERT-based model, finetuned on a diverse array of email datasets. The application significantly enhances the precision of phishing detection mechanisms, adeptly reducing the incidence of successful phishing attacks. Initial tests have demonstrated a precision rate of over 95% in detecting phishing emails, outperforming traditional rule-based filters substantially. The application exhibits robust defences against zero-day phishing attacks through its advanced machine learning framework, which dynamically adapts to emerging phishing strategies. This paper explores the methodology of developing the DistilBERT model, evaluates its efficacy against existing solutions, and discusses its implications for future cybersecurity practices. The study’s findings underscore the potential of AI-driven tools in transforming cybersecurity measures, offering a proactive approach to thwarting phishing attempts and safeguarding sensitive data.

Sunn pest is one of the most crucial noxious species in agriculture. As the sunn pest penetrates and makes damage to the grains, they can no longer be utilized to make bakery goods like bread, pasta, and other baked foods since they become unusable. Therefore, analysis and detection of damaged wheat grains are necessary for production to continue. We recommend that the dataset could be used for analysis and segmentation of the wheat grains, detection of the sunn pest damage condition, and classification of the 6 species of which the dataset consists. As mentioned, in our dataset, there are 6 different species of wheat, including Bezostaja, Müfitbey, Nacibey, Sönmez-2001, Tosunbey, and Ekiz, which are the species that were made in Türkiye. Our dataset differs from the others due to its various species and the condition, whether it is healthy or sunn pest damaged or broken wheat grain, and because the dataset is a multiclass one, it can be used for the classification of the varieties. On the other hand, when the sunn pest damage condition is taken into account, the dataset is suitable for the detection of the sunn pest damage. In addition to that, the dataset includes grains that touch each other which makes it more applicable to problems that arise in real-life. The dataset consists of 83 sunn pest damaged and 87 healthy wheat images. In addition, there are 170 images that contain 3565 wheat grains. As can be observed, the dataset contains a variety of wheat species with sunn pest affected which displays that the promised dataset is suitable for numerous machine learning problems such as classification, segmentation, and detection.

The location and number data of individual fruit trees are critical for planting area investigation, fruit yield prediction, and smart orchard management and planning. These data are conventionally obtained through manual investigation and statistics with time-consuming and laborious effort. Object detection models in deep learning used widely in computer vision could provide an opportunity for accurate detection of individual fruit trees, which is essential for rapidly obtaining the data and reducing human operations errors. This study proposes an approach to detecting individual fruit trees and mapping their spatial distribution by integrating deep learning with unmanned aerial vehicle (UAV) remote sensing. UAV remote sensing collected high-resolution true-color images of fruit trees in the experimental pomelo tree orchards in Meizhou city, South China. An image dataset of deep learning samples of individual pomelo trees (IPTs) was constructed through visual interpretation and field investigation based on the fruit tree images captured by UAV remote sensing. Four different scales of YOLOv5 (YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x) for object detection were selected to train, validate, and test on the image dataset of pomelo trees. The results show that the average precision (AP@0.5) of the four YOLOv5 models for validation reach 87.8%, 88.5%, 89.1%, and 90.7%, respectively. The larger the model scale, the higher the average accuracy of the detection result of validation. It suggests that YOLOv5x is a preferred high-accuracy model among the YOLOv5 family and is suitable to realize the detection of IPTs. The number of the IPTs in the study area was counted using YOLOv5x, and their spatial distribution map was made using the non-maximum suppression method and ArcGIS software. This study will provide primary data and technical support for smart orchard management in Meizhou city and other fruit-producing areas.

Building energy consumption plays an essential role in urban sustainability. The prediction of the energy demand is also of particular importance for developing smart cities and urban planning. Machine learning has recently contributed to the advancement of methods and technologies to predict demand and consumption for building energy systems. This paper presents a state of the art of machine learning models and evaluates the performance of these models. Through a systematic review and a comprehensive taxonomy, the advances of machine learning are carefully investigated and promising models are introduced.

Recent improvements in deepfake creation have made deepfake videos more realistic. Moreover, open-source software has made deepfake creation more accessible, which reduces the barrier to entry for deepfake creation. This could pose a threat to the people’s privacy. There is a potential danger if the deepfake creation techniques are used by people with an ulterior motive to produce deepfake videos of world leaders to disrupt the order of countries and the world. Therefore, research into the automatic detection of deepfaked media is essential for public security. In this work, we propose a deepfake detection method using upper body language analysis. Specifically, a many-to-one LSTM network was designed and trained as a classification model for deepfake detection. Different models were trained by varying the hyperparameters to build a final model with benchmark accuracy. We achieved 94.39% accuracy on the deepfake test set. The experimental results showed that upper body language can effectively detect deepfakes.

This paper explores the application of machine learning (ML) algorithms in predicting trends in the fixed bond market, where traditional analytical methods have proven inadequate. Focusing on various ML techniques such as supervised and unsupervised learning, neural networks, and deep learning, the study evaluates their effectiveness in forecasting market movements. It details a series of experiments in which different ML models are rigorously trained and tested against historical bond market data. The findings reveal that models employing time series analysis and advanced deep learning show marked potential in accurately predicting bond market trends. Additionally, the paper delves into the challenges and limitations inherent in these ML approaches, including data requirements and the risk of model overfitting. Finally, it proposes directions for future research, emphasizing the integration of ML into broader financial market analysis.

Background: Processing whole-slide images (WSI) to train neural networks can be intricate and laborious. We developed an open-source library covering recurrent tasks in processing of WSI and in evaluating the performance of the trained networks for classification tasks. Methods: Two histopathology use-cases were selected. First we aimed to train a CNN to distinguish H&amp;E-stained slides obtained from neuropathologically classified low-grade epilepsy-associated dysembryoplastic neuroepithelial tumor (DNET) and ganglioglioma (GG). The second project we trained a convolutional neural network (CNN) to predict the hormone expression of pituitary adenoms only from hematoxylin and eosin (H&amp;E) stained slides. In the same approach, we addressed the issue to also predict clinically silent corticotroph adenoma. We included four clinico-pathological disease conditions in a multilabel approach. Results: Our best performing CNN achieved an area under the curve (AUC) of 0.97 for the receiver operating characteristic (ROC) for corticotroph adenoma, 0.86 for silent corticotroph adenoma and 0.98 for gonadotroph adenoma. Our DNET-GG classifier achieved an AUC of 1.00 for the ROC curve. All scores were calculated with the help of our library on predictions on a case basis. Conclusions: Our comprehensive library is most helpful to standardize the work-flow and minimize the work-burden in training CNN. It is also compatible with fastai. Indeed, our new CNNs reliably extracted neuropathologically relevant information from the H&amp;E staining only. This approach will supplement the clinico-pathological diagnosis of brain tumors, which is currently based on cost-intense microscopic examination and variable panels of immunohistochemical stainings.

Amyloid PET imaging plays a crucial role in the diagnosis and research of Alzheimer's disease (AD), allowing non-invasive detection of amyloid-β plaques in the brain. However, the low spatial resolution of PET scans limits accurate quantification of amyloid deposition due to partial volume effects (PVE). In this study, we propose a novel approach to addressing PVE using a latent diffusion model for resolution recovery (LDM-RR) of PET imaging. We leverage a synthetic data generation pipeline to create high-resolution PET digital phantoms for model training. The proposed LDM-RR model incorporates a weighted combination of L1, L2, and MS-SSIM losses at both noise and image scales to enhance MRI-guided reconstruction. We evaluated the model's performance in improving statistical power for detecting longitudinal changes and enhancing agreement between amyloid PET measurements from different tracers. Results demonstrate that the LDM-RR approach significantly improves PET quantification accuracy, reduces inter-tracer variability, and enhances the detection of subtle changes in amyloid deposition over time. We show that deep learning has the potential to improve PET quantification in AD, effectively contributing to early detection and monitoring of disease progression.

Computer Vision using Deep Learning algorithms has served numerous human activity identification applications, particularly those linked to safety and security. However, despite the fact that autistic children are frequently exposed to danger as a result of their activities, many Computer Vision experts have shown little interest in their safety. High-grade autistic children frequently experience the Meltdown Crisis condition, characterized by hostile behaviors and loss of control. This study aims to introduce a monitoring system capable of predicting the Meltdown Crisis condition early and alerting the children’s parents or caregivers before entering more difficult settings. For this endeavor, the suggested system was constructed using a combination of a pre-trained Vision Transformer (ViT) model (Swin-3D-b) and a Residual Network (ResNet) architecture to extract robust features from video sequences in order to extract and learn the spatial and temporal features of the Stereotyped Motor Movements made by autistic children at the beginning of the Meltdown Crisis state, which is referred to as the Pre-Meltdown Crisis state. In order to attain a 92% recall and F1 Score, the final decisions made for data preparation, model construction, and training parameters were tweaked and established experimentally. The best loss value obtained was 0.08. The MeltdownCrisis dataset, which includes realistic scenarios of autistic children’s behaviors in the Pre-Meltdown Crisis state and Normal state the Normal state data being used as a negative class was utilized for evaluation.

ChatGPT, developed by OpenAI, is an advanced large language model (LLM) that leverages artificial intelligence (AI) and deep learning to generate human-like responses. This paper explores its applications in digital health and healthcare, focusing on enhancing patient engagement through medical history collection, symptom assessment, and decision support to improve diagnostic accuracy. We also examine its role in promoting health literacy and clinical decision-making across various organ systems. Despite its advantages, the integration of ChatGPT in healthcare poses limitations and risks, including the potential for inaccurate information, overreliance by users, and ethical concerns related to informed consent. We discuss the challenges of keeping pace with rapidly evolving medical knowledge and highlight the need for continuous updates. Additionally, the paper addresses intellectual property and regulatory issues associated with AI deployment in medicine. Through this analysis, we provide insights into the benefits and potential risks of employing ChatGPT in healthcare.

Background: The skin prick test (SPT) is used to diagnose sensitization to antigens. This study proposes a deep learning approach to infer wheal dimensions, aiming to reduce dependence on human interpretation. Methods: A dataset of SPT images (n=5844) was used to infer a convolutional neural network for wheal segmentation (ML model). Three methods for inferring wheal dimensions were evaluated: the ML model; the standard protocol (MA1); and approximation of the area as an ellipse using diameters measured by an allergist (MA2). The results were compared with assisted image segmentation (AIS), the most accurate method. Bland-Altman, distribution analyses, and correlation tests were applied to compare the methods. The study also compared the percentage deviation among these methods in determining the area of wheals with regular geometric shapes (n = 150) and with irregular shapes (n=150). Results: The Bland-Altman analysis showed that the difference between methods was not correlated with the absolute area. The ML model achieved a segmentation accuracy of 85.88% and a strong correlation with the AIS method (ρ=0.88), outperforming all other methods. Additionally, MA1 showed significant error (13.44±13.95%) for pseudopods. Conclusions: The ML protocol can potentially automate the reading of SPT, offering greater accuracy than the standard protocol.

Early diagnosis of paroxysmal atrial fibrillation (PAF) could suggest patients to receive timely interventions in clinical practice. Various PAF onset prediction algorithms might benefit from accurate heart rate variability (HRV) analysis and machine learning classification but to be challenged in real-time monitoring scenarios. The aim of this study is to present an end-to-end deep learning based PAFNet model that integrates a sliding window technique on raw R-R interval of electrocardiogram (ECG) segments to achieve a real-time prediction of PAF onsets. This integration enable the deep convolutional neural network (CNN) to be customized as a light-weight architecture that accommodates the size of sliding windows simply by altering the input layer, specifically its effectiveness in making a new prediction with each new heartbeat. Catering to potential influence of input sizes, three CNN models were trained using 50, 100, and 200 R-R intervals, respectively. For each model, the performance of automated algorithms was evaluated for PAF prediction using a ten-fold cross-validation. As a results, a total of 56,381 PAFN-type and 56,900 N-type R-R interval segments was collected from publicly accessible ECG databases, and a promising prediction performance of the automated algorithm with a 100 R-R intervals was achieved in terms of the sensitivity of 97.12%, the specificity of 97.77%, and the accuracy of 97.45%, respectively. Importantly, the automated algorithm with a sliding windows step of 1 could process one sample in only 23.1 milliseconds and identify the onset of PAF at least 45 minutes in advance. The present results suggest that the sliding window technique on raw R-R interval sequences along by deep learning based algorithms may offers the possibility of providing an accurate, real-time, and end-to-end clinical tool for mass monitoring of PAF.

Cold-water coral (CWC) reefs represent vulnerable marine ecosystems (VMEs) of critical ecological importance. This study presents a novel approach for the automated detection and segmentation of key CWC species, Desmophyllum pertusum and Madrepora oculata, in underwater imagery using the YOLOv8l-seg deep learning model. The model was applied to images collected at two Natura 2000 sites in the Cantabrian Sea: the Avilés Canyon System (ACS) and El Cachucho Seamount (CSM). Results demonstrate the model's high accuracy in identifying and delineating individual coral colonies. Significant variability in coral cover was observed between and within the study areas, highlighting the patchy nature of CWC habitats. Three distinct coral community groups were identified based on percentage coverage composition and abundance, with the highest coral cover group being located exclusively in the La Gaviera canyon head within the ACS. This research demonstrated the potential of deep learning models for efficient and accurate monitoring of VMEs, facilitating the acquisition of high-resolution data essential for understanding CWC distribution, abundance, and community structure, and contributing to the development of effective conservation strategies.

Accurate and timely prediction of Napa cabbage (Brissica rapa subsp. Perkinensis) fresh weight is crucial for optimizing harvest timing, crop management, and supply chain logistics, contributing to food security and price stabilization. Traditional manual sampling methods are labor-intensive and imprecise. This study addresses this challenge by developing a comprehensive (artificial intelligence) AI-powered model for predicting Napa cabbage fresh weight using unmanned aerial vehicle (UAV)-based multi-sensor data. High-resolution RGB, multispectral, and thermal infrared (TIR) imagery were collected over a Napa cabbage field throughout the 2020 growing season. Various vegetation indices, crop features (vegetation fraction, crop height model), and water stress indi-cators (CWSI) were extracted from the imagery. Three AI algorithms—deep neural network (DNN), support vector machine (SVM), and random forest (RF)—were trained and evaluated, with the DNN model consistently outperforming the others. The DNN model achieved the highest accuracy (R² = 0.86 for training, 0.82 for testing; root mean square error (RMSE) = 0.432 kg for training, 0.465 kg for testing) during the mid-to-late rosette growth stage (DAP 35-42), highlighting this period as crucial for fresh weight estimation due to stable leaf area and well-developed canopy structure. The model tended to underestimate the weight of Napa cabbages exceeding 5 kg, potentially due to limited samples and saturation effects of vegetation indices. However, the overall error rate was less than 5%, demonstrating the feasibility and effectiveness of this approach. Spatial analysis revealed that the model accurately captured the variability in Napa cabbage growth across different soil types and irrigation conditions, particularly reflecting the positive impact of drip irrigation on the sandy loam plot. Bias analysis indicated the DNN model's tendency to overestimate smaller Napa cabbages (2 kg), suggesting areas for future refinement. This study demonstrates the potential of UAV-based multi-sensor data and AI algorithms for accurate and non-invasive prediction of Napa cabbage fresh weight. The developed DNN model offers a promising tool for optimizing harvest timing, improving crop management practices, and en-hancing supply chain efficiency. Future research should focus on refining the model for specific weight ranges and diverse environmental conditions, as well as extending its application to other crops, to further advance precision agriculture and contribute to sustainable food production.